TSP: Temporally-Sensitive Pretraining of Video Encoders for Localization Tasks
Open accessThe DOI matches its Crossref record; 27 of the 27 references it cites were found in a registry or an index.
Abstract
Due to the large memory footprint of untrimmed videos, current state-of-the-art video localization methods operate atop precomputed video clip features. These features are extracted from video encoders typically trained for trimmed action classification tasks, making such features not necessarily suitable for temporal localization. In this work, we propose a novel supervised pretraining paradigm for clip features that not only trains to classify activities but also considers background clips and global video information to improve temporal sensitivity. Extensive experiments show that using features trained with our novel pretraining strategy significantly improves the performance of recent state-of-the-art methods on three tasks: Temporal Action Localization, Action Proposal Generation, and Dense Video Captioning. We also show that our pretraining approach is effective across three encoder architectures and two pretraining datasets. We believe video feature encoding is an important building block for localization algorithms, and extracting temporally-sensitive features should be of paramount importance in building more accurate models. The code and pretrained models are available on our project website.
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
You Only Look Once: Unified, Real-Time Object Detection
Redmon, J., Divvala, S., Girshick, R., & Farhadi, A. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.91 · Cited by 53,803
Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation
Chen, L.-C., Zhu, Y., Papandreou, G., Schroff, F., & Adam, H. (2018) · arXiv · doi:10.48550/arxiv.1802.02611 · Cited by 20,063
Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation
Chen, L.-C., Zhu, Y., Papandreou, G., Schroff, F., & Adam, H. (2018) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-01234-2_49 · Cited by 20,054
EfficientDet: Scalable and Efficient Object Detection
Tan, M., Pang, R., & Le, Q. V. (2019) · arXiv · Cited by 9,841 · cited 1×
“Empowered by such capability, many image models are trained in an end-to-end manner for complex tasks such as object detection [59, 60, 67], semantic segmentation [10, 23, 26], and image captionconcat”
BackgroundHoward, A., Sandler, M., Chen, B., Wang, W., Chen, L.-C., Tan, M., Chu, G., Vasudevan, V., Zhu, Y., Pang, R., et al. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00140 · Cited by 9,708
Learning Spatiotemporal Features with 3D Convolutional Networks
Tran, D., Bourdev, L., Fergus, R., Torresani, L., & Paluri, M. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.510 · Cited by 9,593
Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset
Carreira, J., & Zisserman, A. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.502 · Cited by 9,570
Large-Scale Video Classification with Convolutional Neural Networks
Karpathy, A., Toderici, G., Shetty, S., Leung, T., Sukthankar, R., & Fei-Fei, L. (2014) · 2014 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2014.223 · Cited by 6,354 · cited 2×
“State-of-theart methods for these localization tasks use features extracted from video encoders typically pretrained for the task of Trimmed Action Classification (TAC) on large-scale datasets, such as Kinetics [32] and Sports-1M [31].”
MethodUcf101: 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
Research works printed but not linked: 64
- 10.1109/CVPR.2018.00751 · DOI · Paper page
- 10.1109/CVPR.2018.00675 · DOI · Paper page
- 10.1109/CVPR.2019.00037 · DOI · Paper page
- 10.1007/978-3-030-01252-6_29 · DOI
- 10.1109/CVPR.2018.00782 · DOI · Paper page
- 10.1007/978-3-319-46484-8_2 · DOI · Paper page
- 10.1145/3394171.3413860 · DOI
- 10.1109/CVPR.2018.00443 · DOI · Paper page
- 10.1109/CVPR.2019.01058 · DOI · Paper page
- 10.1109/ICCV.2017.617 · DOI · Paper page
- korbar, 2018, Cooperative learning of audio and video models from self-supervised synchronization, NeurIPS
- jain, 2020, Action-bytes: Learning from trimmed videos to localize actions, CVPR
- 10.1609/aaai.v34i07.6793 · DOI · Paper page
- 10.1109/ICCV.2017.83 · DOI · Paper page
- 10.1109/ICCV.2019.00633 · DOI · Paper page
- ren, 2015, Faster r-cnn: Towards real-time object detection with region proposal networks, NeurIPS
- 10.1109/CVPR.2017.155 · DOI · Paper page
- 10.18653/v1/P19-1641 · DOI
- iashin, 2020, Multi-modal dense video captioning, cvprw
- 10.1007/978-3-030-01270-0_10 · DOI · Paper page
- iashin, 2020, A better use of audio-visual cues: Dense video captioning with bi-modal transformer, BMVC
- 10.1109/CVPR.2016.119 · DOI · Paper page
- simonyan, 2014, Two-stream convolutional networks for action recognition in videos, Advances in neural information processing systems
- 10.1016/j.cviu.2016.10.018 · DOI · Paper page
- 10.1109/CVPR42600.2020.01079 · doi:10.1109/cvpr42600.2020.01079 · Paper page
- 10.1109/ICCV.2019.00565 · DOI · Paper page
- alwassel, 2018, Action search: Spotting targets in videos and its application to temporal action localization, ECCV
- alwassel, 2018, Victor Escorcia, and Bernard Ghanem. Diagnosing error in temporal action detectors, ECCV
- 10.1109/CVPR.2019.01232 · DOI · Paper page
- 10.1109/ICME46284.2020.9102850 · DOI
- 10.1109/ICCV.2017.322 · DOI · Paper page
- 10.1109/ICCV.2019.00901 · DOI
- 10.1109/CVPR.2019.00675 · DOI
- 10.1109/ICCV.2019.00900 · DOI
- 10.1109/CVPR.2018.00556 · DOI
- 10.1109/CVPR.2019.00854 · DOI · Paper page
- 10.1007/978-3-030-01225-0_35 · DOI · Paper page
- 10.1109/WACV48630.2021.00336 · DOI
- 10.1109/CVPR.2014.326 · DOI
- 10.1609/aaai.v34i07.6815 · DOI · Paper page
- 10.1109/ICCV.2017.610 · DOI · Paper page
- 10.1007/978-3-319-46487-9_47 · DOI · Paper page
- 10.1109/TPAMI.2013.65 · DOI · Paper page
- 10.1007/978-3-030-01216-8_5 · DOI · Paper page
- yan, 2019, Stat: spatial-temporal attention mechanism for video captioning, TMM
- 10.1609/aaai.v34i07.6711 · DOI
- 10.1109/CVPR42600.2020.01017 · DOI · Paper page
- 10.1109/CVPR.2016.503 · DOI · Paper page
- xu, 2019, Text-to-clip video retrieval with early fusion and re-captioning, AAAI
- 10.1109/CVPR.2018.00911 · DOI · Paper page
- 10.1109/CVPR.2018.00636 · DOI · Paper page
- 10.1109/CVPR.2017.675 · DOI · Paper page
- 10.1007/978-3-030-58604-1_8 · DOI
- 10.1109/ICCV.2019.00719 · DOI · Paper page
- 10.1007/978-3-030-58548-8_25 · DOI
- 10.1007/978-3-030-58598-3_32 · DOI · Paper page
- 10.1109/CVPR42600.2020.01311 · DOI · Paper page
- 10.1109/CVPR.2018.00124 · DOI · Paper page
- 10.1109/ICCV.2019.00400 · DOI
- 10.1109/CVPR.2019.00372 · DOI · Paper page
- 10.1109/CVPR.2017.345 · DOI · Paper page
- 10.1109/ICCV.2019.00718 · DOI · Paper page
- 10.1609/aaai.v34i07.6829 · DOI · Paper page
- lin, 2018, Bsn: Boundary sensitive network for temporal action proposal generation, ECCV
Cited by
ActionFormer: Localizing Moments of Actions with Transformers
Zhang, C.-L., Wu, J., & Li, Y. (2022) · Lecture Notes in Computer Science · doi:10.1007/978-3-031-19772-7_29 · Cited by 435
End-to-End Temporal Action Detection With Transformer
Liu, X., Wang, Q., Hu, Y., Tang, X., Zhang, S., Bai, S., & Bai, X. (2022) · IEEE Transactions on Image Processing · doi:10.1109/tip.2022.3195321 · Cited by 282
(2023) · doi:10.1109/cvpr52729.2023.01808 · Cited by 226
Hear Me out: Fusional Approaches for Audio Augmented Temporal Action Localization
Bagchi, A., Mahmood, J., Fernandes, D., & Sarvadevabhatla, R. (2022) · Proceedings of the 17th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications · doi:10.5220/0010832700003124 · Cited by 29
RefineTAD: Learning Proposal-free Refinement for Temporal Action Detection
Feng, Y., Zhang, Z., Quan, R., Wang, L., & Qin, J. (2023) · Proceedings of the 31st ACM International Conference on Multimedia · doi:10.1145/3581783.3611872 · Cited by 8
“Following previous works [32, 39], we adopt TSP R(2+1)D [2] to extract the video feature.”
Method
Metadata
- Authors
- Alwassel, H., Giancola, S., & Ghanem, B.
- Venue
- 2021 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW)
- Publisher
- IEEE
- Published
- 2021-10
- Pages
- 3166-3176
- OpenAlex
- W3107327400
- Cited by
- 123
- References
- 27
- FWCI
- 8.06
- Type
- conference paper
- Language
- en
- Open access
- green
- Licence
- Funders
- King Abdullah University of Science and Technology
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
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: TSP: Temporally-Sensitive Pretraining of Video Encoders for Localization Tasks. https://app.cochat.ai/papers/10.1109/iccvw54120.2021.00356
- The paper
- Alwassel, H., Giancola, S., & Ghanem, B. (2021). TSP: Temporally-Sensitive Pretraining of Video Encoders for Localization Tasks. 2021 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW). https://doi.org/10.1109/iccvw54120.2021.00356
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.