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
Items 101–149 of 149
Mélange fabric image retrieval based on soft similarity learning
Xiang, J., Pan, R., & Gao, W. (2022) · Journal of Engineered Fibers and Fabrics · doi:10.1177/15589250221088896 · Cited by 5
“Wu et al. 38 presented a novel unsupervised deep video hashing for fast large-scale similarity search, which integrates feature learning and hash function learning in a self-taught manner.”
BackgroundUnsupervised Learning of Spatio-Temporal Representation with Multi-Task Learning for Video Retrieval
Kumar, V. (2022) · National Conference on Communications · doi:10.1109/ncc55593.2022.9806811 · Cited by 7
“Similarly for fast pace p=4, the 8 frame video sequence is form by sampling 8 frames with skipping p-1 frames (e.g., 1, 5, 9, 13, 17, 21, 25, 29).”
BackgroundMethodDeep Hybrid Neural Network With Attention Mechanism for Video Hash Retrieval Method
Wu, K., & Li, X. (2023) · IEEE Access · doi:10.1109/access.2023.3276321 · Cited by 5
“video Hashing (UDVH) proposed in literature [27] aims to learn compact and effective binary hash code representing video features, and make the information contained in each dimension of the hash code as equal as possible by using balanced rotation.”
BackgroundA Deep Analysis of Image Based Video Searching Techniques
Anayat, S., Sikandar, A., Rasheed, S. A., & Butt, S. (2020) · International Journal of Wireless and Microwave Technologies · doi:10.5815/ijwmt.2020.04.05 · Cited by 7
“Large scale experiments performed on popular videos dataset which manifest that UDVH is best than the state of art in period of estimation metrics[22].”
BackgroundKalakoti, G., & Prabakaran, G. (2020) · Traitement du signal · doi:10.18280/ts.370509 · Cited by 6
“Wu et al. [51] have proposed a deep hashing method, called Unsupervised Deep Video Hashing, for large-scale video similarity search to learn compact and more effective binary codes.”
MethodCross-Domain Image-Object Retrieval Based on Weighted Optimal Transport
Hu, N., Huang, X., Li, W., Li, X., & Liu, A.-A. (2023) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2023.3254889 · Cited by 7
“The features derived from these two domains also follow different distributions [7], [8], [9], which results in poor retrieval performance by directly matching 2D images to 3D objects.”
BackgroundAVHash: Joint Audio-Visual Hashing for Video Retrieval
Zhou, Y., Sun, Z., Liu, R., Chen, Y., & Zhang, D. (2024) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3664647.3681266 · Cited by 8
PCNet: Paired channel feature volume network for accurate and efficient depth estimation
Jia, D., Pang, Y., Cao, J., et al. (2022) · Neurocomputing · doi:10.1016/j.neucom.2022.09.024 · Cited by 3
Akbacak, E. (2023) · Multimedia Tools and Applications · doi:10.1007/s11042-023-17810-8 · Cited by 4
“Unsupervised methods do not need labelled video data [43, 44].”
Chen, H., Huang, W. X., & Zhang, T. (2025) · International Journal of Multimedia Information Retrieval · doi:10.1007/s13735-025-00355-x · Cited by 7
“Video object detection is an important task for applications such as autonomous driving perception [1, 2], intelligent surveillance [3, 4] and video retrieval [5, 6 ].”
Are You Watching Closely? Content-based Retrieval of Hand Gestures
Parian, M. A., Rossetto, L., Schuldt, H., & Dupont, S. (2020) · International Conference on Multimedia Retrieval · doi:10.1145/3372278.3390723 · Cited by 3
“These methods are either based on vectors obtained from the activation of fully connected layers [37] or intermediate layers of CNNs [18], or by using the regional maximum activation of convolutions [32] which is based on the output of Region of Interest (ROI) pooling layers of sampled frames from…”
MethodDistributed Supervised Discrete Hashing With Relaxation
Hu, R., Ye, M., Ma, C., & Chen, F. (2021) · IEEE Access · doi:10.1109/access.2021.3074947 · Cited by 3
“The representative algorithms are iterative quantization (ITQ) [4], [5], anchor graph hashing (AGH) [6], unsupervised deep video hashing (UDVH) [7] and spectral hashing (SP) [8], [9].”
MethodTop Position Sensitive Ordinal Relation Preserving Bitwise Weight for Image Retrieval
Wang, Z., Sun, F., Zhang, L., Wang, L., & Liu, P. (2020) · Algorithms · doi:10.3390/a13010018 · Cited by 3
A temporal attention based appearance model for video object segmentation
Wang, H., Liu, W., & Xing, W. (2021) · Applied Intelligence · doi:10.1007/s10489-021-02547-4 · Cited by 5
Discrete Semantics-Guided Asymmetric Hashing for Large-Scale Multimedia Retrieval
Long, J., Sun, L., Hua, L., & Yang, Z. (2021) · Applied Sciences · doi:10.3390/app11188769 · Cited by 3
“Unsupervised Deep Video Hashing (UDVH) [30] learns the hash codes in a self-taught manner by jointly integrating discriminative video representation with optimal code learning.”
BackgroundWeighted‐Attribute Triplet Hashing for Large‐Scale Similar Judicial Case Matching
Li, J., Liu, X., Nie, X., Ma, L., Li, P., Zhang, K., & Yin, Y. (2021) · Computational Intelligence and Neuroscience · doi:10.1155/2021/6650962 · Cited by 5
Content Based Video Retrieval—Methods, Techniques and Applications
Mounika, B., Palanisamy, P., & Khare, A. (2021) · Studies in big data · doi:10.1007/978-3-030-75657-4_4 · Cited by 2
Maze: A Cost-Efficient Video Deduplication System at Web-scale
Qin, A., Xiao, M., Huang, B., & Zhang, X. (2022) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3503161.3548145 · Cited by 5
“On the other hand, CNN-based features understand the videos as a whole so that they are compact and cost-efficient [20, 28, 41, 46].”
BackgroundDUO: Stealthy Adversarial Example Attack on Video Retrieval Systems via Frame-Pixel Search
Yao, X., Zhan, Y., Chen, Y., Tang, F., Zhao, M., Li, E., & Zhang, Y. (2023) · IEEE International Conference on Distributed Computing Systems (ICDCS) · doi:10.1109/icdcs57875.2023.00044 · Cited by 3
“Note that UCF101 has a larger size than HMDB51.”
MethodInfluentialVideo Analysis Based on Human Pose for Unsupervised Summarization and Retrieval
Santiago, C., Alves, D. M., Ferreira, B. Q., de Carvalho, J. R. F. G., Messina, A., & Costeira, J. P. (2019) · International Workshop on Content-Based Multimedia Indexing (CBMI) · doi:10.1109/cbmi.2019.8877437 · Cited by 3
“applying generic feature extractors may lead to poor results, as unbalanced feature relevances may cause hashing-based methods to yield lower performances [18, 19].”
BackgroundDiscriminative Codebook Hashing for Supervised Video Retrieval
Bian, X., Lan, R., Wang, X., Chen, C., Liu, Z., Luo, X., & Lai, K. (2021) · Computational Intelligence and Neuroscience · doi:10.1155/2021/5845094 · Cited by 3
“In recent years, hashing methods proposed for video retrieval have also received extensive attention [24–31] and are composed of two categories: machine learning methods and deep hashing.”
MethodRobust Data-Aware Sensing Based on Half Quadratic Hashing for the Visual Internet of Things
Chen, B.-W., & Huang, J.-Y. (2022) · IEEE Internet of Things Journal · doi:10.1109/jiot.2022.3163748 · Cited by 2
Zero-Shot Learning with Missing Attributes using Semantic Correlations
Braytee, A., Naji, M., Anaissi, A., Chaturvedi, K., & Prasad, M. (2021) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn52387.2021.9533591 · Cited by 3
“First framework is the most popular framework which aims to learn a projection function to map the visual features to semantic space [2], [3], [11].”
Video action re-localization using spatio-temporal correlation
Ramaswamy, A., Seemakurthy, K., Gubbi, J., & Balamuralidhar, P. (2022) · IEEE/CVF Winter Conference on Applications of Computer Vision Workshops (WACVW) · doi:10.1109/wacvw54805.2022.00025 · Cited by 2
“The common approach is to compare the feature vector of a query video with that of each of the videos in the reference database [15, 27].”
BackgroundMultifaceted Analysis of Fine-Tuning in a Deep Model for Visual Recognition
Li, X., Herranz, L., & Jiang, S. (2020) · ACM/IMS Transactions on Data Science · doi:10.1145/3319500 · Cited by 2
“e a deep model which integrates deep convolutional networks with binary latent representation learning. Li et al. [27] combine CNN and recursive neural network (RNN) for visual recognition. Wu et al. [54] propose a model where feature learning and hash function learning are jointly integrated. However, for many object…”
BackgroundEncode the Unseen: Predictive Video Hashing for Scalable Mid-stream Retrieval
Yu, T., & Padoy, N. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-69541-5_26 · Cited by 5
Targeted Attack for Deep Hashing based RetrievalPreprint
Bai, J., Chen, B., Li, Y., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2004.07955 · Cited by 2
“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.”
Similarity Preserving Transformer Cross-Modal Hashing for Video-Text Retrieval
Huang, Q., Peng, S., Shen, X., Yuan, Y.-H., & Pan, S. (2024) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3664647.3681606 · Cited by 6
“Unsupervised deep cross-modal hashing [10, 32, 36] performs joint learning of feature and latent hash code in an end-to-end manner by optimizing an unsupervised loss.”
Temporal Map-Based Boundary Refinement Network for Video Moment Localization
Lyu, L., Liu, D., Zhang, C., Zhang, Y., Ruan, H., & Zhu, L. (2025) · Electronics · doi:10.3390/electronics14081657 · Cited by 2
AV-NAS: Audio-Visual Multi-Level Semantic Neural Architecture Search for Video Hashing
Chen, Y., Zhou, Y., Dong, H., Liu, R., Lin, Z., & Zhang, D. (2025) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/3726302.3729899 · Cited by 3
“Video hashing [35, 38, 50, 51, 55] aims to produce semantic binary vectors for videos, drastically cutting storage needs and boosting retrieval speeds in information retrieval contexts.”
Unique hash value based identical video sharing traffic flow optimization across social networks
Konyak, C. Y., & Baydeti, N. (2024) · Multimedia Tools and Applications · doi:10.1007/s11042-024-19441-z · Cited by 1
Zhou, H., Li, J., Liu, X., Lyu, Y., Chen, H., & Liu, A.-A. (2024) · Multimedia Systems · doi:10.1007/s00530-024-01431-8 · Cited by 1
“It usually discovers the relevant "supervised" information in the unsupervised scenario by different reconstruction strategies [9, 10, 10, 14, 28, 29], such as the reconstruction of 3D shape from itself with different data formats, including multi-view, voxel, and point cloud, or from the context…”
A Ranking-Based Hashing Algorithm Based on the Distributed Spark Platform
Yang, A., Qian, J., Chen, H., et al. (2020) · Information · doi:10.3390/info11030148 · Cited by 1
“Representative unsupervised hashing methods include locality-sensitive hashing (LSH) [7], spectral hashing (SH) [8], self-taught hashing (STH) [9], iterative quantization (ITQ) [10], unsupervised deep video hashing (UDVH) [11], and principal component analysis hashing (PCAH) [12].”
Pairwise Context Similarity for Image Retrieval System Using Variational Auto-Encoder
Yun, H., Kim, Y., Kang, T., & Jung, K. (2021) · IEEE Access · doi:10.1109/access.2021.3061765 · Cited by 2
“[32] proposed an unsupervised deep-learning-tohash framework for large scale video retrieval task, reporting the state-of-the-arts performances.”
BackgroundWITHDRAWN: Neural architecture search based on model pool for wildlife identification
Jia, L., Feng, W., Chen, C., & Zhang, J. (2020) · Neurocomputing · doi:10.1016/j.neucom.2020.03.035 · Cited by 1
RetractedEncode the Unseen: Predictive Video Hashing for Scalable Mid-Stream RetrievalPreprint
Yu, T., & Padoy, N. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2009.14661 · Cited by 1
2019 Index IEEE Transactions on Image Processing Vol. 28
(2019) · IEEE Transactions on Image Processing · doi:10.1109/tip.2019.2959522 · Cited by 1
Compact feature learning for multimedia retrieval
Liong, V. E. (2019) · doi:10.32657/10220/48655
“Content-based Retrieval data-independent Submodular Video Hashing [98] subspace modeling VHDT [99] covariance modeling CVC [103] unsupervised deep modeling SSVH [102], UDVH [101]”
BackgroundMethodShuffle and Learn: Minimizing Mutual Information for Unsupervised HashingPreprint
Liu, F., & Liu, Z. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2011.10239
“It is also capable of carrying sufficient information in application like multimedia retrieval [4], [5] without concern on annotations.”
BackgroundA novel multilabel video retrieval method using multiple video queries and deep hash codes
Akbacak, E. (2022) · Concurrency and Computation Practice and Experience · doi:10.1002/cpe.6927
Deep multi-query video retrieval
Akbacak, E., & Vural, C. (2022) · Journal of Visual Communication and Image Representation · doi:10.1016/j.jvcir.2022.103501
Manifold Similarity Reconstruction based Video Hashing
Zhou, Y., Huang, Q., & Shen, X. (2022) · International Conference on High Performance Big Data and Intelligent Systems (HPBD&IS) · doi:10.1109/hdis56859.2022.9991567
Visual-Semantics Embedding for Deep Hashing-Based Multi-Label Video RetrievalPreprint
Yue, Y., Zou, Q., Cao, L., Yu, H., Chen, C., & Li, N. (2023) · SSRN Electronic Journal · doi:10.2139/ssrn.4663643
Extremely Compact Video Representation for Efficient Near-Duplicates DetectionPreprint
Fojcik, K., Syga, P., & Klonowski, M. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4815120
A Novel Intelligent Model for Video Retrieval Based Onvision Transformer (Vit)Preprint
Younis, A. N., & Ramo, F. M. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5144625
Multi-view Correlation Learning Cross-Modal Retrieval Based on Multi-layer Attention
Han, Z., Azman, A., Khalid, F., et al. (2025) · Lecture notes in electrical engineering · doi:10.1007/978-981-96-2244-3_46
Zhang, T., & Yuan, X. (2025) · Journal of Electronic Imaging · doi:10.1117/1.jei.34.2.023047
Video-to-Video Retrieval Using a Multidimensional (3D) CNN and Hash methodPreprint
Gharahsouflou, A., Maihami, V., & Khamforoosh, K. (2025) · Research Square · doi:10.21203/rs.3.rs-7085737/v1
Near-Duplicate Video Retrieval Based on Deep Hashing and Graph Matching
Zhang, F. (2025) · International Conference on Electronic Information Engineering and Computer Communication (EIECC) · doi:10.1109/eiecc67963.2025.11409525
“…optimization" strategy, effectively avoiding information loss from traditional separate binarization; the unsupervised deep video hashing method [2] balances hash code dimension variance via a "balanced rotation" technique, addressing weak expressive ability of traditional hash codes; the…”
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.