Query - Dependent Video Representation for Moment Retrieval and Highlight Detection
Open accessThe DOI matches its Crossref record; 12 of the 12 references it cites were found in a registry or an index.
Abstract
Recently, video moment retrieval and highlight detection (MR/HD) are being spotlighted as the demand for video understanding is drastically increased. The key objective of MR/HD is to localize the moment and estimate clip-wise accordance level, i.e., saliency score, to the given text query. Although the recent transformer-based models brought some advances, we found that these methods do not fully exploit the information of a given query. For example, the relevance between text query and video contents is sometimes neglected when predicting the moment and its saliency. To tackle this issue, we introduce Query-Dependent DETR (QD-DETR), a detection transformer tailored for MR/HD. As we observe the insignificant role of a given query in transformer architectures, our encoding module starts with cross-attention layers to explicitly inject the context of text query into video representation. Then, to enhance the model's capability of exploiting the query information, we manipulate the video-query pairs to produce irrelevant pairs. Such negative (irrelevant) video-query pairs are trained to yield low saliency scores, which in turn, encourages the model to estimate precise accordance between query-video pairs. Lastly, we present an input-adaptive saliency predictor which adaptively defines the criterion of saliency scores for the given video-query pairs. Our extensive studies verify the importance of building the query-dependent representation for MR/HD. Specifically, QD-DETR outperforms state-of-the-art methods on QVHighlights, TVSum, and Charades-STA datasets. Codes are available at github.com/wjun0830IQD-DETR.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474
Focal Loss for Dense Object Detection
Lin, T.-Y., Goyal, P., Girshick, R., He, K., & Dollar, P. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.324 · Cited by 30,581
End-to-End Object Detection with Transformers
Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., & Zagoruyko, S. (2020) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-58452-8_13 · Cited by 18,285
End-to-End Object Detection with Transformers
Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., & Zagoruyko, S. (2020) · arXiv · doi:10.48550/arxiv.2005.12872 · Cited by 18,253
Generalized Intersection Over Union: A Metric and a Loss for Bounding Box Regression
Rezatofighi, H., Tsoi, N., Gwak, J., Sadeghian, A., Reid, I., & Savarese, S. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00075 · Cited by 6,612 · cited 1×
“It consists of a L1 loss and a generalized IoU loss LgIoU(·) from previous work [37] with minor modification to localize temporal moments.”
BackgroundDeformable DETR: Deformable Transformers for End-to-End Object Detection
Zhu, X., Su, W., Lu, L., Li, B., Wang, X., & Dai, J. (2020) · arXiv · doi:10.48550/arxiv.2010.04159 · Cited by 6,027 · cited 1×
“Since then, along with the advance in DETR [10, 25, 60], DETRlike architectures have been popular in downstream tasks in both the image [8, 9, 20, 58] and video domains [23, 51].”
BackgroundMasked-attention Mask Transformer for Universal Image Segmentation
Cheng, B., Misra, I., Schwing, A. G., Kirillov, A., & Girdhar, R. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.00135 · Cited by 3,565 · cited 1×
“Since then, along with the advance in DETR [10,25,60], DETRlike architectures have been popular in downstream tasks in both the image [8, 9, 20, 58] and video domains [23, 51].”
BackgroundPANNs: Large-Scale Pretrained Audio Neural Networks for Audio Pattern Recognition
Kong, Q., Cao, Y., Iqbal, T., Wang, Y., Wang, W., & Plumbley, M. D. (2020) · IEEE/ACM Transactions on Audio, Speech, and Language Processing · doi:10.1109/taslp.2020.3030497 · Cited by 1,235 · cited 1×
“Additionally, we use the PANN [27] model trained on AudioSet [17] to extract audio features1 for experiments with the audio modality.”
MethodDN-DETR: Accelerate DETR Training by Introducing Query DeNoising
Li, F., Zhang, H., Liu, S., Guo, J., Ni, L. M., & Zhang, L. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.01325 · Cited by 1,102
Conditional DETR for Fast Training Convergence
Meng, D., Chen, X., Fan, Z., Zeng, G., Li, H., Yuan, Y., Sun, L., & Wang, J. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00363 · Cited by 1,055
Dynamic DETR: End-to-End Object Detection with Dynamic Attention
Dai, X., Chen, Y., Yang, J., Zhang, P., Yuan, L., & Zhang, L. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00298 · Cited by 456 · cited 1×
“Since then, along with the advance in DETR [10,25,60], DETRlike architectures have been popular in downstream tasks in both the image [8, 9, 20, 58] and video domains [23, 51].”
BackgroundDN-DETR: Accelerate DETR Training by Introducing Query DeNoising
Li, F., Zhang, H., Liu, S., Guo, J., Ni, L. M., & Zhang, L. (2022) · arXiv · doi:10.48550/arxiv.2203.01305 · Cited by 57
Metadata
- Authors
- Moon, W., Hyun, S., Park, S., Park, D., & Heo, J.-P.
- Venue
- 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
- Publisher
- IEEE
- Published
- 2023-06
- Pages
- 23023-23033
- ISSN
- 1063-6919 (ISSN-L)
- OpenAlex
- W4386083094
- Cited by
- 164
- References
- 12
- FWCI
- 18.65
- Type
- conference paper
- Language
- en
- Open access
- green
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.
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.