Unsupervised Deep Video Hashing via Balanced Code for Large-Scale Video Retrieval
Open accessThe DOI matches its Crossref record; 81 of the 96 references it cites were found in a registry or an index; 6 of the 38 sources its claims cite were checked for support.
Abstract
This paper proposes a deep hashing framework, namely Unsupervised Deep Video Hashing (UDVH), for largescale video similarity search with the aim to learn compact yet effective binary codes. Our UDVH produces the hash codes in a self-taught manner by jointly integrating discriminative video representation with optimal code learning, where an efficient alternating approach is adopted to optimize the objective function. The key differences from most existing video hashing methods lie in 1) UDVH is an unsupervised hashing method that generates hash codes by cooperatively utilizing feature clustering and a specifically-designed binarization with the original neighborhood structure preserved in the binary space; 2) a specific rotation is developed and applied onto video features such that the variance of each dimension can be balanced, thus facilitating the subsequent quantization step. Extensive experiments performed on three popular video datasets show that UDVH is overwhelmingly better than the state-of-the-arts in terms of various evaluation metrics, which makes it practical in real-world applications.
Overview
CoChat Summary
TL;DR
The paper proposes Unsupervised Deep Video Hashing (UDVH), a self-taught deep hashing framework that jointly learns video representations and balanced binary codes via feature clustering, CCA, and a balanced rotation. On FCVID, YFCC, and ActivityNet, UDVH-TSN outperforms state-of-the-art video hashing baselines in retrieval accuracy and training efficiency.
Key findings
- UDVH-TSN achieves mAP@20 of 50.4% on FCVID at 128 bits, 4.8% higher than UDVH-LSTM (45.6%) and 8.9% over SSTH; on YFCC it reaches 29.8% vs. 26.1% and 24%; on ActivityNet it reaches 26.2% vs. 20.7% and 17.8%.
- Precision@100 at 64 bits is 51% on FCVID (at least about 3.6% higher than comparable baselines), 30.2% on YFCC vs. SSTH’s 26.3%, and 26.1% on ActivityNet vs. SSTH’s 20.4%.
- The balanced rotation (CCA-BR) outperforms CCA-ITQ and PCA-BR, producing flatter per-dimension variance; cluster number around 400 gives best mAP@20 at 128 bits (FCVID 0.504, YFCC 0.293, ActivityNet 0.262).
- Training is efficient: UDVH-TSN takes about 0.74–0.81 hours per loop and less than 4.5 hours total, versus over 8 hours for SSTH; balanced rotation costs only seconds.
Methods
- UDVH uses k-means on 10,000 sampled FC7 1024-d video features to generate C pseudo-labels, CCA to project features to k dimensions, and a balanced rotation solved as an orthogonality-constrained l2,1-norm maximization; it alternates updating R, B = sign(H × R), and deep parameters Θ via SGD minimizing ||F(Z; Θ) − B||_F^2, with t = 3–5 loops.
- The deep architecture uses modified Temporal Segment Networks (TSNs) with spatial and temporal ConvNets, fused global-pool features, and two fully connected layers (FC7 and FC8); 20 frames are uniformly sampled per video.
- Experiments use FCVID (91,223 videos, 239 categories; 45,611 train), YFCC (0.7M processed videos; 0.6M unlabeled train, 0.1M labeled test), and ActivityNet (~20,000 clips, 200 categories; ~10,000 train/test; 1,000 queries), comparing against AGH, SubMod, ITQ, SP, MFH, DH, SSTH, and UDVH-LSTM with mAP@K, PR, and Precision@100 at 16/32/64/128 bits.
Limitations
- The paper states ActivityNet gives the worst performance due to many untrimmed videos and large intra-class variance, with improvement there described as “a bit limited”; YFCC performance drops because many videos are low-quality amateur mobile clips; loss-function effects are not obvious (less than 3% improvement).
- Evident from the text: cluster number C, iteration count t, and other hyperparameters are chosen empirically, and the alternating optimization may only find a local optimum.
- Evident from the text: evaluation is limited to three video datasets and a selected set of baselines, and the method is unsupervised, relying on pseudo-labels rather than manual labels.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
0 Valid · 8 Not valid · 22 Not checked · 75 Own results and interpretations
The cited sources that could be checked couldn’t confirm or dispute this claim.
In the paper
“In contrast to Principle Component Analysis (PCA), CCA is more effective in extracting discriminative information with the robustness in anti-noise [3], thus obtaining more discriminative video features after the projection.”
§ IEEE TRANSACTIONS ON IMAGE PROCESSING 1 Unsupervised Deep Video Hashing via Balanced Code for Large-Scale Video Retrieval > A. Feature Embedding with Pseudo Labels
What the sources say
- Could not verifycites [3] sourceExperimental — accuracy not yet measured
Section III describes a kernelized correlation-filter tracker, and the Experimental Settings section says it uses HOG features. Searches for CCA, PCA, and their full names found no passage comparing their discriminative information or noise robustness. The copy therefore does not address the attributed claim. (LLM, conf=0.77)
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Could not verify
The cited sources that could be checked couldn’t confirm or dispute this claim.
In the paper
“Unfortunately, it has been acknowledged that the performance of those hashing schemes may degrade significantly if the projected dimensions are imbalanced [4], [6], [13], i.e., their variances vary a lot.”
§ IEEE TRANSACTIONS ON IMAGE PROCESSING 1 Unsupervised Deep Video Hashing via Balanced Code for Large-Scale Video Retrieval > I. INTRODUCTION
What the sources say
- Not checked — no full text of the sourcecites [4] source
- Could not verifycites [6] sourceExperimental — accuracy not yet measured
Section 7.1 discusses compressing image features into short binary codes for retrieval, but does not address imbalanced projected dimensions or their effect on hashing performance. Searches for hashing, projected dimensions, and variance found no passage in our copy that makes the attributed claim. (LLM, conf=0.76)
- Could not verifycites [13] sourceExperimental — accuracy not yet measured
The Introduction (p. 1) discusses features that may be incompatible with hash coding, while Section 3.3 (p. 4) discusses redundancy among hash bits. Neither addresses whether unequal variances across projected dimensions significantly degrade hashing performance (searched: projected dimensions, imbalanced, variance). (LLM, conf=0.74)
hedgedstates a possible cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
The cited sources that could be checked couldn’t confirm or dispute this claim.
In the paper
“More importantly, our optimization approach transforms the hash function learning into a regression problem with binary code B as the regression target, thus avoiding the use of a relaxation strategy to solve the nonconvex equation with binary constraints in most published works [3], [8], [18], [35], [48], [57], [58].”
§ IEEE TRANSACTIONS ON IMAGE PROCESSING 1 Unsupervised Deep Video Hashing via Balanced Code for Large-Scale Video Retrieval > C. Objective Function and Optimization
What the sources say
- Could not verifycites [3] sourceExperimental — accuracy not yet measured
The cited paper’s Introduction and Weighted Interpolation Updating section describe a visual-tracking method, not hash-function learning. Searches for binary-code regression and relaxation of binary constraints found no passage addressing the point for which this paper is cited. (LLM, conf=0.76)
- Not checked — no full text of the sourcecites [8] source
- Not checked — no full text of the sourcecites [18] source
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Could not verify
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“The results show that the combination of CCA and BR outperforms the other methods on the datasets substantially.”
§ IEEE TRANSACTIONS ON IMAGE PROCESSING 1 Unsupervised Deep Video Hashing via Balanced Code for Large-Scale Video Retrieval > E. Results and Analysis 1) Parameter Analysis:
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper states — it cites no source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Again, it is pretty clear that our BR scheme can always guarantee the flat variance of each dimension, regardless of which video features are used.”
§ IEEE TRANSACTIONS ON IMAGE PROCESSING 1 Unsupervised Deep Video Hashing via Balanced Code for Large-Scale Video Retrieval > E. Results and Analysis 1) Parameter Analysis:
boostedstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
53 more claims
Create a free account to see all 105 claims and every source verdict.
- It may state two separate claims as one. 42
- Probably not a substantial claim. 7
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
Each contradiction between two passages listed here was confirmed by an independent check.
Rated major: it would touch a result — a value a result rests on, reported and recomputed p-values on opposite sides of the significance level, two passages that conflict with no sign which is right, or a cited work retracted before this paper was published.
In the paper
§ IEEE TRANSACTIONS ON IMAGE PROCESSING 1 Unsupervised Deep Video Hashing via Balanced Code for Large-Scale Video Retrieval > 5) Comparison with State-of-The-Arts:
“the mAP@20 values of UDVH-TSN (29.8%) and UDVH-LSTM (26.1%) at 128 bits”
§ IEEE TRANSACTIONS ON IMAGE PROCESSING 1 Unsupervised Deep Video Hashing via Balanced Code for Large-Scale Video Retrieval > C. Implementation Details
“YFCC [64] 0.201 0.274 0.293 0.289 0.291”
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
§ IEEE TRANSACTIONS ON IMAGE PROCESSING 1 Unsupervised Deep Video Hashing via Balanced Code for Large-Scale Video Retrieval > D. Complexity Analysis
“the time complexity is O(k 3 ) in (15) in solving B”
§ IEEE TRANSACTIONS ON IMAGE PROCESSING 1 Unsupervised Deep Video Hashing via Balanced Code for Large-Scale Video Retrieval > C. Objective Function and Optimization
“B = sign(H × R), s.t. H ∈ R N ×k , R ∈ R k×k . (15”
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
§ IEEE TRANSACTIONS ON IMAGE PROCESSING 1 Unsupervised Deep Video Hashing via Balanced Code for Large-Scale Video Retrieval > III. UNSUPERVISED DEEP VIDEO HASHING
“Those network parameters will be updated automatically during each iteration of hash function learning”
§ IEEE TRANSACTIONS ON IMAGE PROCESSING 1 Unsupervised Deep Video Hashing via Balanced Code for Large-Scale Video Retrieval > C. Implementation Details
“the mini-batch back-propagation is only performed in the FC7 and FC8 layers”
Citations
Cites
Very Deep Convolutional Networks for Large-Scale Image Recognition
Simonyan, K., & Zisserman, A. (2014) · arXiv · doi:10.48550/arxiv.1409.1556 · Cited by 114,148
ImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155
Hochreiter, S., & Schmidhuber, J. (1997) · Neural Computation · doi:10.1162/neco.1997.9.8.1735 · Cited by 102,318
Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
Ioffe, S., & Szegedy, C. (2015) · arXiv · doi:10.48550/arxiv.1502.03167 · Cited by 27,818
Representation Learning: A Review and New Perspectives
Bengio, Y., Courville, A., & Vincent, P. (2013) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2013.50 · Cited by 13,001
Two-Stream Convolutional Networks for Action Recognition in Videos
Simonyan, K., & Zisserman, A. (2014) · arXiv · doi:10.48550/arxiv.1406.2199 · Cited by 6,756
The relationship between Precision-Recall and ROC curves
Davis, J., & Goadrich, M. (2006) · Proceedings of the 23rd international conference on Machine learning - ICML '06 · doi:10.1145/1143844.1143874 · Cited by 6,559
Large-Scale Machine Learning with Stochastic Gradient Descent
Bottou, L. (2010) · Proceedings of COMPSTAT'2010 · doi:10.1007/978-3-7908-2604-3_16 · Cited by 5,795 · cited 2×
“(16) This minimization problem can be solved by fine-tuning the deep network with Stochastic Gradient Descent (SGD) [61] until it gets converged, where the Euclidean loss is minimized via mini-batch back-propagation and the low bound can be found (See IV-C).”
BackgroundUcf101: A dataset of 101 human actions classes from videos in the wild
Soomro, K., Zamir, A. R., & Shah, M. (2012) · arXiv · doi:10.48550/arxiv.1212.0402 · Cited by 4,575
Approximate nearest neighbors: towards removing the curse of dimensionality
Indyk, P., & Motwani, R. (1998) · Proceedings of the thirtieth annual ACM symposium on Theory of computing - STOC '98 · doi:10.1145/276698.276876 · Cited by 4,188
Research works printed but not linked: 3
- over, 2014, enot, “TRECVID 2014—An overview of the goals, tasks, data, evaluation mechanisms and metrics, Proc TRECVID, 52
- xu, 2013, Harmonious hashing, Proc IJCAI, 1820
- liu, 2011, Hashing with graphs, Proc ICML, 1
Cited by
RGB-T Salient Object Detection via Fusing Multi-Level CNN Features
Zhang, Q., Huang, N., Yao, L., Zhang, D., Shan, C., & Han, J. (2020) · IEEE Transactions on Image Processing · doi:10.1109/tip.2019.2959253 · Cited by 247
“classification [72], object tracking [73], [74] and instance-level object retrieval [75], [76].”
BackgroundSelf-citationLearning Modality-Consistency Feature Templates: A Robust RGB-Infrared Tracking System
Lan, X., Ye, M., Shao, R., Zhong, B., Yuen, P. C., & Zhou, H. (2019) · IEEE Transactions on Industrial Electronics · doi:10.1109/tie.2019.2898618 · Cited by 128
“Efforts have been made in this field, and the decade has witnessed numerous tracking algorithms proposed to handle a variety of research issues [1]–[29].”
BackgroundRethinking Triplet Loss for Domain Adaptation
Deng, W., Zheng, L., Sun, Y., & Jiao, J. (2020) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2020.2968484 · Cited by 108
Adaptive Label Correlation Based Asymmetric Discrete Hashing for Cross-modal Retrieval
Li, H., Zhang, C., Jia, X., Gao, Y., & Chen, C. (2021) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2021.3102119 · Cited by 99
“More recently, the great success of deep learning has inspired the study of deep hashing methods [21], [22], [23], [24], [25], [26], [27].”
BackgroundDeep Salient Object Detection With Contextual Information Guidance
Liu, Y., Han, J., Zhang, Q., & Shan, C. (2019) · IEEE Transactions on Image Processing · doi:10.1109/tip.2019.2930906 · Cited by 96
“Besides, we will apply our salient object detector to facilitate the representation ability of existing deep networks [73], [74] and real-world applications, including image retrieval [75], [76] and image classification [77].”
MethodSelf-citationInfluence-Aware Attention Networks for Anomaly Detection in Surveillance Videos
Zhang, S., Gong, M., Xie, Y., Qin, A. K., Li, H., Gao, Y., & Ong, Y.-S. (2022) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2022.3148392 · Cited by 104
Muhammad, K., Hussain, T., Ser, J. D., Palade, V., & de Albuquerque, V. H. C. (2019) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2019.2960536 · Cited by 99
“The compact representation of long videos is helpful in many video analytics applications, including action and activity recognition [2], [3] and retrieval [4], [5].”
BackgroundInteractive Video Retrieval in the Age of Deep Learning – Detailed Evaluation of VBS 2019
Rossetto, L., Gasser, R., Lokoč, J., Bailer, W., Schoeffmann, K., Münzer, B., Souček, T., Nguyen, P. A., Bolettieri, P., Leibetseder, A., et al. (2020) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2020.2980944 · Cited by 92
“These meth-ods produce a wide range of descriptor sizes, which has also led to the application of deep-learning methods to the problem of hashing [16] in order to construct compact representations of the video content.”
BackgroundDeep balanced discrete hashing for image retrieval
Zheng, X., Zhang, Y., & Lu, X. (2020) · Neurocomputing · doi:10.1016/j.neucom.2020.04.037 · Cited by 83
Targeted Attack for Deep Hashing Based Retrieval
Bai, J., Chen, B., Li, Y., Wu, D., Guo, W., Xia, S., & Yang, E. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-58452-8_36 · Cited by 110
“Moreover, some of the unsupervised video hashing methods were also proposed [49,28], which organize the hash code learning in a self-taught manner to reduce the time and labor consuming labeling.”
Semantics-Aware Spatial-Temporal Binaries for Cross-Modal Video Retrieval
Qi, M., Qin, J., Yang, Y., Wang, Y., & Luo, J. (2021) · IEEE Transactions on Image Processing · doi:10.1109/tip.2020.3048680 · Cited by 107
FIVR: Fine-Grained Incident Video Retrieval
Kordopatis-Zilos, G., Papadopoulos, S., Patras, I., & Kompatsiaris, I. (2019) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2019.2905741 · Cited by 79
“Some representative approaches include [16], [25], [41]–[43], [48].”
BackgroundMethodWu, S. (2021) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2021.3098461 · Cited by 72
ST-CNN: Spatial-Temporal Convolutional Neural Network for crowd counting in videos
Miao, Y., Han, J., Gao, Y., & Zhang, B. (2019) · Pattern Recognition Letters · doi:10.1016/j.patrec.2019.04.012 · Cited by 71
Self-citationScene Recognition With Prototype-Agnostic Scene Layout
Chen, G., Song, X., Zeng, H., & Jiang, S. (2020) · IEEE Transactions on Image Processing · doi:10.1109/tip.2020.2986599 · Cited by 71
“sification [13], [27], object detection [28], semantic segmentation [29], and many other vision tasks [30]–[32].”
BackgroundWhere to Prune: Using LSTM to Guide Data-Dependent Soft Pruning
Ding, G., Zhang, S., Jia, Z., Zhong, J., & Han, J. (2020) · IEEE Transactions on Image Processing · doi:10.1109/tip.2020.3035028 · Cited by 71
“…hand, use LSTM model to guide other filter pruning algorithms, including C-SGD [60] and GSC [61];and on the other hand, apply the proposed model compression method to simplify deep models for different visual tasks, such as video retrieval [62], image classification [63] and 3D reconstruction [64].”
MethodSelf-citationM-GCN: Multi-Branch Graph Convolution Network for 2D Image-based on 3D Model Retrieval
Nie, W., Ren, M., Liu, A.-A., Mao, Z., & Nie, J. (2020) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2020.3006371 · Cited by 59
“For the unsupervised retrieval problem, a deep hashing framework named unsupervised deep video hashing (UDVH) is proposed by Wu et al. [18].”
MethodSelf-supervised Video Hashing via Bidirectional Transformers
Li, S., Li, X., Lu, J., & Zhou, J. (2021) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr46437.2021.01334 · Cited by 67
Dual‐domain reconstruction network with V‐Net and K‐Net for fast MRI
Liu, X., Pang, Y., Jin, R., Liu, Y., & Wang, Z. (2022) · Magnetic Resonance in Medicine · doi:10.1002/mrm.29400 · Cited by 53
Neighborhood Preserving Hashing for Scalable Video Retrieval
Li, S., Chen, Z., Lu, J., Li, X., & Zhou, J. (2019) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00830 · Cited by 57
STRONG: Spatio-Temporal Reinforcement Learning for Cross-Modal Video Moment Localization
Cao, D., YaWen, Z., Liu, M., He, X., Wang, M., & Qin, Z. (2020) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3394171.3413840 · Cited by 44
“For example, the video retrieval [35] aims to retrieve videos from a set of collections to match the given language query.”
BackgroundDeep discrete hashing with pairwise correlation learning
Chen, Y., & Lu, X. (2019) · Neurocomputing · doi:10.1016/j.neucom.2019.12.078 · Cited by 48
Deep Category-Level and Regularized Hashing With Global Semantic Similarity Learning
Chen, Y., & Lu, X. (2020) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2020.2964993 · Cited by 45
Multi-layer Attention Based CNN for Target-Dependent Sentiment Classification
Zhang, S., Xu, X., Pang, Y., & Han, J. (2019) · Neural Processing Letters · doi:10.1007/s11063-019-10017-9 · Cited by 49
Self-citationUnsupervised Variational Video Hashing With 1D-CNN-LSTM Networks
Li, S., Chen, Z., Li, X., Lu, J., & Zhou, J. (2019) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2019.2946096 · Cited by 47
“Wu et al. [39] proposed Unsupervised Deep Video Hashing (UDVH) which aimed to balance the variation of each dimension of the hash code.”
BackgroundLabel-activating framework for zero-shot learning
Liu, Y., Gao, X., Gao, Q., Han, J., & Shao, L. (2019) · Neural Networks · doi:10.1016/j.neunet.2019.08.023 · Cited by 41
Self-citationGraph and Autoencoder Based Feature Extraction for Zero-shot Learning
Liu, Y., Xie, D., Gao, Q., Han, J., Wang, S., & Gao, X. (2019) · International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2019/421 · Cited by 45
Self-citationAnuranji, R., & Srimathi, H. (2020) · Digital Signal Processing · doi:10.1016/j.dsp.2020.102729 · Cited by 40
Liu, Y., Pang, Y., Liu, X., Liu, Y., & Nie, J. (2022) · Neurocomputing · doi:10.1016/j.neucom.2022.09.048 · Cited by 44
Multisample-Based Contrastive Loss for Top-K Recommendation
Tang, H., Zhao, G., Wu, Y., & Qian, X. (2021) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2021.3126146 · Cited by 48
SAR image change detection based on deep denoising and CNN
Cao, X., Ji, Y., Wang, L., Ji, B., Jiao, L., & Han, J. (2019) · IET Image Processing · doi:10.1049/iet-ipr.2018.5172 · Cited by 37
Self-citationDeep learning for video-text retrieval: a review
Zhu, C., Jia, Q. F., Chen, W., Guo, Y., & Liu, Y. (2023) · International Journal of Multimedia Information Retrieval · doi:10.1007/s13735-023-00267-8 · Cited by 66
“One solution is to design new hashing strategies [39, 108, 109] which are widespread in image and video retrieval for storage and searching while having not been researched much for the VTR task.”
BackgroundSelf-citationSketch-Based Image Retrieval With Multi-Clustering Re-Ranking
Wang, L., Qian, X., Zhang, X., et al. (2019) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2019.2959875 · Cited by 35
“I N ORDER to search the desired images for internet users, text-based image retrieval (TBIR) [1]–[3], [54]–[57] has been widely applied, and content-based image/video retrieval [4]–[9], [53], [58] also emerge.”
BackgroundLearning Segment Similarity and Alignment in Large-Scale Content Based Video Retrieval
Jiang, C., Huang, K., He, S., Yang, X., Zhang, W., Zhang, X., Cheng, Y., Yang, L., Wang, Q., Xu, F., et al. (2021) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3474085.3475301 · Cited by 47
“Deep hash [18, 19] transforms features into binary codes for fast Hamming distance computation.”
MethodZhang, S., Wu, G., Gu, J., & Han, J. (2020) · Electronics · doi:10.3390/electronics9081209 · Cited by 43
“Additionally, in future work, we will use our technique to compress deep CNN architectures for various applications, such as visual tracking [52–54], video analysis [55,56], and large-scale visual search [57,58].”
MethodSelf-citationWang, X., Zhao, X., & Ren, J. (2019) · Complexity · doi:10.1155/2019/8641074 · Cited by 35
“Wu (2018) proposed an unsupervised deep hashing framework and adopted an efficient alternating approach to optimize the objective function [25].”
BackgroundChen, H., Hu, C., Lee, F., Lin, C., Yao, W., Lü, C., & Chen, Q. (2021) · Sensors · doi:10.3390/s21093094 · Cited by 39
“Unsupervised deep video hashing (UDVH) [46] utilizes feature clustering and a specific rotation to balance the variance of each dimension.”
MethodA novel Siamese deep hashing model for histopathology image retrieval
Alizadeh, S. M., Helfroush, M. S., & Müller, H. (2023) · Expert Systems with Applications · doi:10.1016/j.eswa.2023.120169 · Cited by 40
Online Non-Negative Multi-Modality Feature Template Learning for RGB-Assisted Infrared Tracking
Lan, X., Ye, M., Shao, R., Zhong, B., Jain, D. K., & Zhou, H. (2019) · IEEE Access · doi:10.1109/access.2019.2916895 · Cited by 29
“video surveillance [1]–[22], image and video classification [23]–[36], image retrieval [37], [38], image quality assessment and processing [39]–[45]), unmanned vehicle [46], machine learning (e.”
BackgroundAggregation Signature for Small Object Tracking
Liu, C., Ding, W., Yang, J., Murino, V., Zhang, B., Han, J., & Guo, G. (2019) · IEEE Transactions on Image Processing · doi:10.1109/tip.2019.2940477 · Cited by 40
“Furthermore, our approach will be extended to different applications in the future, such as large-scale retrieval [43], [44] and classification [45].”
MethodSelf-citationWeakly Supervised Deep Semantic Segmentation Using CNN and ELM with Semantic Candidate Regions
Xu, X., Li, G., Xie, G., Ren, J., & Xie, X. (2019) · Complexity · doi:10.1155/2019/9180391 · Cited by 28
Text-Based Localization of Moments in a Video Corpus
Paul, S., Mithun, N. C., & Roy–Chowdhury, A. K. (2021) · IEEE Transactions on Image Processing · doi:10.1109/tip.2021.3120038 · Cited by 28
“Most of the video-text retrieval approaches [15], [16], [17], [18], [19], [20], [21], [22] are designed for cases where videos and text queries have a one-to-one correspondence, i.”
BackgroundSupervised Discrete Multiple-Length Hashing for Image Retrieval
Nie, X., Liu, X., Guo, J., Wang, L., & Yin, Y. (2022) · IEEE Transactions on Big Data · doi:10.1109/tbdata.2022.3161905 · Cited by 31
“As one of the important techniques in ANN search, hashing has become more and more popular for conducting fast retrieval in the large-scale database, as it is superior to the other methods in real scenarios [2], [3], [4], [5], [6].”
MethodDeep Quadruple-Based Hashing for Remote Sensing Image-Sound Retrieval
Chen, Y., Xiong, S., Mou, L., & Zhu, X. X. (2022) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2022.3155283 · Cited by 31
“Wu et al. [33] leveraged a self-taught manner to learn unsupervised deep hash functions.”
BackgroundCognitive computing on unstructured data for customer co-innovation
Chen, S., Kang, J. S., Liu, S., & Sun, Y. (2019) · European Journal of Marketing · doi:10.1108/ejm-01-2019-0092 · Cited by 37
Multi-scale Triplet Hashing for Medical Image Retrieval
Chen, Y., Tang, Y., Huang, J., & Xiong, S. (2023) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2023.106633 · Cited by 30
Attention-Based Video Hashing for Large-Scale Video Retrieval
Wang, Y., Nie, X., Shi, Y., Zhou, X., & Yin, Y. (2019) · IEEE Transactions on Cognitive and Developmental Systems · doi:10.1109/tcds.2019.2963339 · Cited by 30
Learning Transformation-Invariant Local Descriptors With Low-Coupling Binary Codes
Miao, Y., Lin, Z., Ma, X., Ding, G., & Han, J. (2021) · IEEE Transactions on Image Processing · doi:10.1109/tip.2021.3106805 · Cited by 25
Self-citationA multi-embedding neural model for incident video retrieval
Chiang, T.-H., Tseng, Y., & Tseng, Y. (2022) · Pattern Recognition · doi:10.1016/j.patcog.2022.108807 · Cited by 28
Zhang, Q., Huo, Z., Liu, Y., Pan, Y., Shan, C., & Han, J. (2019) · Pattern Recognition · doi:10.1016/j.patcog.2019.03.023 · Cited by 21
Self-citationImage Captioning with Memorized Knowledge
Chen, H., Ding, G., Lin, Z., Guo, Y., Shan, C., & Han, J. (2019) · Cognitive Computation · doi:10.1007/s12559-019-09656-w · Cited by 26
Self-citationDeep Neighborhood Component Analysis for Visual Similarity Modeling
Liu, X., Yang, X., Wang, M., & Hong, R. (2020) · ACM Transactions on Intelligent Systems and Technology · doi:10.1145/3375787 · Cited by 28
“…and has been successfully applied in many visual analysis problems, such as face recognition [Cai et al. 2012; Lu et al. 2017a], media retrieval [Gengshen et al. 2019; Guo et al. 2017; Hoi et al. 2010; Wei et al. 2016], person re-identification [Yang et al. 2017, 2019], and tracking [Hu et al.…”
BackgroundMethodOnline Discriminative Cross-Modal Hashing
Kang, X., Liu, X., Zhang, X., Nie, X., & Yin, Y. (2023) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2023.3342418 · Cited by 20
“1) Discriminative Semantic Embedding: Enhancing semantic discrimination has been proven to effectively improve retrieval accuracy in the field of hash learning [35], [36].”
BackgroundOn Aggregation of Unsupervised Deep Binary Descriptor With Weak Bits
Wu, G., Lin, Z., Ding, G., Ni, Q., & Han, J. (2020) · IEEE Transactions on Image Processing · doi:10.1109/tip.2020.3025437 · Cited by 21
Self-citationClassification-enhancement deep hashing for large-scale video retrieval
Nie, X., Zhou, X., Shi, Y., Sun, J., & Yin, Y. (2021) · Applied Soft Computing · doi:10.1016/j.asoc.2021.107467 · Cited by 22
A multi-view clustering framework via integrating K-means and graph-cut
Han, L., Gao, Q., Zhang, X., et al. (2022) · Neurocomputing · doi:10.1016/j.neucom.2022.05.120 · Cited by 19
Deep Saliency Smoothing Hashing for Drone Image Retrieval
Chen, Y., Huang, J., Mou, L., Jin, P., Xiong, S., & Zhu, X. X. (2023) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2023.3255302 · Cited by 24
“Wu et al. [55] used the self-taught way to perform unsupervised video hashing learning.”
BackgroundToward efficient indexing structure for scalable content-based music retrieval
Shen, J., Mei, T., Qu, Q., et al. (2019) · Multimedia Systems · doi:10.1007/s00530-019-00613-z · Cited by 19
“In recent years, advanced hashing has been playing more and more important role in support of fast and effective multimedia information retrieval [30–32].”
BackgroundZhang, D., Ding, W., Liu, C., Wang, H., & Zhang, B. (2020) · IEEE Access · doi:10.1109/access.2020.2971586 · Cited by 22
Video hashing with secondary frames and invariant moments
Tang, Z., Zhang, S., Zhang, X., Li, Z., Chen, Z., & Yu, C. (2021) · Journal of Visual Communication and Image Representation · doi:10.1016/j.jvcir.2021.103209 · Cited by 20
Video Hashing with DCT and NMF
Tang, Z., Lv, C., Yao, H., Zhang, X., & Yu, C. (2019) · The Computer Journal · doi:10.1093/comjnl/bxz060 · Cited by 19
Hu, N., Zhou, H., Huang, X., Li, X., & Liu, A.-A. (2022) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2022.3182533 · Cited by 19
“The advantage of using a set of 2D view representations is that it can directly employ the existing powerful CNNs for feature extraction [26]–[32].”
BackgroundDGRNet: A Dual-Level Graph Relation Network for Video Object Detection
Qi, Q., Hou, T., Lu, Y., Yan, Y., & Wang, H. (2023) · IEEE Transactions on Image Processing · doi:10.1109/tip.2023.3285136 · Cited by 19
Towards automating stocktaking in warehouses: Challenges, trends, and reliable approaches
Daios, A., Xanthopoulos, A. S., Folinas, D., et al. (2024) · Procedia Computer Science · doi:10.1016/j.procs.2024.01.142 · Cited by 17
Unsupervised Video Hashing with Multi-granularity Contextualization and Multi-structure Preservation
Hao, Y., Duan, J., Zhang, H., Zhu, B., Zhou, P., & He, X. (2022) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3503161.3547836 · Cited by 20
“In the studied hashing field, there are also a lot of works [4, 5, 23– 27, 41, 51, 57] that use deep neural networks for either/both feature extraction or/and hash code generation.”
BackgroundMethodConsensus Knowledge Exploitation for Partial Query Based Image Retrieval
Zhang, Y., Ji, Z., Pang, Y., & Li, X. (2023) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2023.3281507 · Cited by 16
“…a variety of tasks, such as pedestrian attribute recognition [11], person re-identification [12], image captioning [13], [14], [15], [16], few/zero-shot learning [17], [18], [19], [20], [21], cross-modal retrieval [6], [22], [23], [24], [25], [26], [27], and visual commonsense reasoning [28], [29].”
Zhong, R., Wang, R., Yao, W., Min, H., Dong, S., & Munteanu, A. (2023) · IEEE Transactions on Image Processing · doi:10.1109/tip.2023.3293762 · Cited by 21
“Prior works have made attempts to efficiently perform video summarization [1], [2], [3].”
MethodDeep Learning Based Proactive Caching for Effective WSN‐Enabled Vision Applications
Lei, F., Cai, J., Dai, Q., & Zhao, H. (2019) · Complexity · doi:10.1155/2019/5498606 · Cited by 19
Fine Aligned Discriminative Hashing for Remote Sensing Image-Audio Retrieval
Chen, Y., Huang, J., Xiong, S., & Lu, X. (2023) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2023.3269300 · Cited by 16
“For example, Wu et al. [32] used the network self-learning approach for unsupervised hash codes learning.”
BackgroundMethodTSDTVOS: Target-guided spatiotemporal dual-stream transformers for video object segmentation
Zhou, W., Zhao, Y., Zhang, F., Luo, B., Yu, L., Chen, B., Yang, C., & Gui, W. (2023) · Neurocomputing · doi:10.1016/j.neucom.2023.126582 · Cited by 14
Learnable Central Similarity Quantization for Efficient Image and Video Retrieval
Yuan, L., Wang, T., Zhang, X., Tay, F. E. H., Jie, Z., Tian, Y., Liu, W., & Feng, J. (2023) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2023.3321148 · Cited by 17
“For FCVID and YFCC, we compare our proposed CSQ/CSQ LC against four hashing methods: SSVH [66], NPH [67], BTH [68], and UDVH-TSN [69].”
Cross-modal dual subspace learning with adversarial network
Shang, F., Zhang, H., Sun, J., et al. (2020) · Neural Networks · doi:10.1016/j.neunet.2020.03.015 · Cited by 14
Self-citationIncremental Instance-Oriented 3D Semantic Mapping via RGB-D Cameras for Unknown Indoor Scene
Li, W., Gu, J., Chen, B., et al. (2020) · Discrete Dynamics in Nature and Society · doi:10.1155/2020/2528954 · Cited by 14
“Some other works focus on processing large-scale video retrieval [13–15], but they mainly deal with the entire scene. paper intends to incrementally build instance-ori-ent semantic 3D maps via RGB-D cameras in real time.”
Self-citationFast simultaneous image super-resolution and motion deblurring with decoupled cooperative learning
Liu, H., Qin, J., Fu, Z., Li, X., & Han, J. (2020) · Journal of Real-Time Image Processing · doi:10.1007/s11554-020-00976-x · Cited by 13
Self-citationContrastive Transformer Hashing for Compact Video Representation
Shen, X., Zhou, Y., Yuan, Y., Yang, X., Lan, L., & Zheng, Y. (2023) · IEEE Transactions on Image Processing · doi:10.1109/tip.2023.3326994 · Cited by 16
“For instance, some works [24], [26] reconstruct frames in forward and reverse orders, while other works [19], [27] generate pseudo label or construct similarity matrix.”
BackgroundMethodInfluentialFine-Grained Feature Generation for Generalized Zero-Shot Video Classification
Hong, M., Zhang, X., Li, G., & Huang, Q. (2023) · IEEE Transactions on Image Processing · doi:10.1109/tip.2023.3247167 · Cited by 14
“Cross-modal tasks involving the interaction of multiple modal data are widely used, such as image and video retrieval [49], [50], [51], video summarization [52], [53], text to image and video prediction and synthesis [54], [55], [56], language-driven spatiotemporal action positioning [57], and…”
MethodBoosting Temporal Binary Coding for Large-Scale Video Search
Wu, Y., Liu, X., Qin, H., Xia, K. W., Hu, S., Ma, Y., & Wang, M. (2020) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2020.2978593 · Cited by 12
“Many previous works on video hashing [14], [26], [29], [30], [54]–[57] have treated a video as a collection of independent images and”
BackgroundA novel feature learning framework for high-dimensional data classification
Li, Y., Chai, Y., Yin, H., et al. (2020) · International Journal of Machine Learning and Cybernetics · doi:10.1007/s13042-020-01188-2 · Cited by 12
“Typical feature learning methods include, but not limited to, subspace learning [12, 13], dictionary learning [14–16], deep learning [17–19], hashing-based learning [20], and metric learning [21].”
BackgroundMethodSmart counting of unboxed stocks in the Warehouse 4.0 ecosystem
Balaska, V. E., Folinas, D. K., Konstantinidis, F. K., et al. (2022) · IEEE International Conference on Imaging Systems and Techniques (IST) · doi:10.1109/ist55454.2022.9827758 · Cited by 12
Indoor scene understanding via RGB-D image segmentation employing depth-based CNN and CRFs
Li, W., Gu, J., Dong, Y., Dong, Y., & Han, J. (2019) · Multimedia Tools and Applications · doi:10.1007/s11042-019-07882-w · Cited by 14
Self-citationLive laparoscopic video retrieval with compressed uncertainty
Yu, T., Mascagni, P., Verde, J. M., Marescaux, J., Mutter, D., & Padoy, N. (2023) · Medical Image Analysis · doi:10.1016/j.media.2023.102866 · Cited by 11
Attention-based deep supervised hashing for near duplicate video retrieval
Shi, N., Fu, C., Tie, M., Zhang, W., Wang, X., & Sham, C. (2023) · Neural Computing and Applications · doi:10.1007/s00521-023-09342-x · Cited by 13
“Two years later, an analogous UDVH framework [41] was proposed, with the key differentiation being its reliance on temporal segment network (TSN) [42].”
A Survey on Near Duplicate Video Retrieval Using Deep Learning Techniques and Framework
Phalke, D. A., & Jahirabadkar, S. A. (2020) · IEEE Pune Section International Conference (PuneCon) · doi:10.1109/punecon50868.2020.9362347 · Cited by 10
“In [4], the use of pre-trained TSNs (Temporal Segment Network) model is done to extract the frame level spatial and temporal features from video clips.”
MethodInfluentialStructure-Adaptive Neighborhood Preserving Hashing for Scalable Video Search
Li, S., Li, X., Lu, J., & Zhou, J. (2021) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2021.3093258 · Cited by 16
Spatiotemporal two-stream LSTM network for unsupervised video summarization
Min, H., Hu, R., Wang, Z., Xiong, Z., & Zhong, R. (2022) · Multimedia Tools and Applications · doi:10.1007/s11042-022-12901-4 · Cited by 13
“The video summarization representing an original video through a brief sketch is an alternative method to achieve efficient browsing and propagation [13, 35, 45].”
MethodSiamese Dilated Inception Hashing With Intra-Group Correlation Enhancement for Image Retrieval
Lu, X., Chen, Y., & Li, X. (2019) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2019.2935118 · Cited by 12
“[31] developed a novel unsupervised deep video hashing (UDVH) algorithm, which can leverage feature clustering and a particularly designed binarization to generate compact hash codes.”
BackgroundSelf-Supervised Temporal Sensitive Hashing for Video Retrieval
Li, Q., Tian, X., & Ng, W. W. Y. (2024) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2024.3385183 · Cited by 13
“The UDVH [6] tries to optimize by rotating the binary code as ITQ to balance information contained in every hash bit.”
MethodACMNet: Adaptive Confidence Matching Network for Human Behavior Analysis via Cross-modal Retrieval
Chen, H., Ding, G., Lin, Z., Zhao, S., Gu, X., Xu, W., & Han, J. (2020) · ACM Transactions on Multimedia Computing Communications and Applications · doi:10.1145/3362065 · Cited by 9
“…analysis on single modality, e.g., human gesture recognition [22], video tracking [43, 58–60], image classification [11, 18], video retrieval [52], there exist many fundamental problems to be solved for cross-modality human behavior analysis, such as learning common representations of human…”
BackgroundSelf-citationSemantic-Preserving Surgical Video Retrieval With Phase and Behavior Coordinated Hashing
Yang, Y., Wang, H., Wang, J., Dong, K., & Ding, S. (2023) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2023.3321382 · Cited by 9
“To preserve the original neighborhood structure of videos and facilitate quantization of binary codes, unsupervised deep video hashing [35] uses feature clustering with a specifically designed binarization to generate hash codes and adopts a rotation onto video features to balance the variance of…”
MethodBased on Spatial and Temporal Implicit Semantic Relational Inference for Cross-Modal Retrieval
Jin, M., Hu, W., Zhu, L., Wang, X., & Hong, R. (2024) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2024.3411298 · Cited by 8
Content based video retrieval using dynamic textures
Mounika, B., Palanisamy, P., Sekhar, H. H., et al. (2022) · Multimedia Tools and Applications · doi:10.1007/s11042-022-13086-6 · Cited by 8
“[34] has developed an unsupervised hashing algorithm for the retrieval of large scale videos.”
MethodDeep Weibull hashing with maximum mean discrepancy quantization for image retrieval
Feng, H., Wang, N., & Tang, J. (2021) · Neurocomputing · doi:10.1016/j.neucom.2021.08.090 · Cited by 9
Practical protection against video data leakage via universal adversarial head
Bai, J., Chen, B., Gao, K., Wang, X., & Xia, S. (2022) · Pattern Recognition · doi:10.1016/j.patcog.2022.108834 · Cited by 15
Dual-Resolution Dual-Path Convolutional Neural Networks for Fast Object Detection
Pan, J. S., Sun, H., Song, Z., & Han, J. (2019) · Sensors · doi:10.3390/s19143111 · Cited by 8
“In future work, we will apply our object detector to facilitate real-world applications, including image retrieval [35,36], image tracking [37], and image classification [38].”
MethodSelf-citationYin, X., & Chen, L. (2022) · Scientific Programming · doi:10.1155/2022/7314599 · Cited by 11
“Different from the existing multimodal CAE models [32, 33], while learning the representations of different modes, respectively, this method generates some association between the representations of each mode through a feature association module (i.”
MethodExtremely compact video representation for efficient near-duplicates detection
Fojcik, K., Syga, P., & Klonowski, M. (2024) · Pattern Recognition · doi:10.1016/j.patcog.2024.111016 · Cited by 9
Efficient Unsupervised Video Hashing With Contextual Modeling and Structural Controlling
Duan, J., Hao, Y., Zhu, B., Cheng, L., Zhou, P., & Wang, X. (2024) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2024.3368924 · Cited by 8
“[44] takes CNN features and then uses deep learning to learn hash function, while [45] explores video information by additionally extracting optical flow features, which prove to be useful in video understanding.”
Unsupervised Video Summarization with Independently Recurrent Neural Networks
Yalınız, G., & İkizler-Cinbiş, N. (2019) · Signal Processing and Communications Applications Conference (SIU) · doi:10.1109/siu.2019.8806603 · Cited by 6
“Video özetleme; video dizinleme, bilgi çıkarımı, olay tespiti gibi diğer alanlara kullanışlı bir altyapı sağlayabilir [2], [3].”
El-Morshedy, M., Fathalla, R., & El-Sonbaty, Y. (2022) · Applied Sciences · doi:10.3390/app12031713 · Cited by 5
Model authentication hashing: Identifying pirated neural network models
Xiong, C., Feng, G., Sun, Y., Qian, Z., Yao, H., & Qin, C. (2025) · Expert Systems with Applications · doi:10.1016/j.eswa.2025.127706 · Cited by 7
Metadata
- Authors
- Wu, G., Han, J., Guo, Y., Liu, L., Ding, G., Ni, Q., & Shao, L.
- Affiliations
- Lancaster University (GB)
- Tsinghua University (CN)
- Inception Institute of Artificial Intelligence (AE)
- Venue
- IEEE Transactions on Image Processing
- Published
- 2019-04
- Volume
- 28
- Issue
- 4
- Pages
- 1993-2007
- ISSN
- 1057-7149 (ISSN-L)
- 1941-0042
- OpenAlex
- W2900790473
- Cited by
- 148
- References
- 96
- Citations by year
- 2026: 2 · 2025: 9 · 2024: 9 · 2023: 21 · 2022: 24 · 2021: 22 · 2020: 29 · 2019: 32
- FWCI
- 10.38
- Type
- journal article
- Language
- en
- Open access
- green
- eprints.lancs.ac.uk
- Licence
- Locations
- IEEE Transactions on Image Processing (publishedVersion)
- PubMed (publishedVersion)
- Lancaster EPrints (Lancaster University) (acceptedVersion)
- Warwick Research Archive Portal (University of Warwick) (submittedVersion)
- Funders
- Royal Society (IE150997)
- Shenzhen Government (GJHZ20180419190732022)
- National Natural Science Foundation of China (61773301, 61571269)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Image and Video Retrieval Techniques
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Image Retrieval and Classification Techniques
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Video Analysis and Summarization
- Keywords
- video hashing, binary codes, feature clustering, binarization, quantization, alternating optimization
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
The claim verdicts this report counts are experimental: their accuracy is not yet measured.
A language model drew the claims from the paper on 2026-10-10, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-10-10 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
Cited sources are checked with a language model’s help (gpt-6-sol).
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.