Only Time Can Tell: Discovering Temporal Data for Temporal Modeling
Open accessThe DOI matches its Crossref record; 11 of the 11 references it cites were found in a registry or an index.
Abstract
Understanding temporal information and how the visual world changes over time, is a fundamental ability of intelligent systems. In video understanding, temporal information is at the core of many current challenges, including compression, efficient inference, motion estimation or summarization. However, in current video datasets it has been observed that action classes can often be recognized without any temporal information, from a single frame of video. As a result, both benchmarking and training in these datasets may give an unintentional advantage to models with strong image understanding capabilities, as opposed to those with strong temporal understanding. In other words, current datasets may not reward good temporal understanding, potentially hindering progress. In this paper we address this problem head on by identifying action classes where temporal information is actually necessary to recognize them and call these "temporal classes". Selecting temporal classes using a computational method would bias the process. Instead, we propose a methodology based on a simple and effective human annotation experiment. We remove just the temporal information, by shuffling frames in time, and measure if the action can still be recognized. Classes that cannot be recognized when frames are not in order, are included in the temporal set. We observe that this set is statistically different from other static classes, and that performance in it correlates with a network's ability to capture temporal information. Thus we use it as a benchmark on current popular networks, which reveals a series of interesting facts, like inflated convolutions bias networks towards classes where motion is not important. We also explore the effect of training on the temporal set, and observe that this leads to better generalization in unseen classes, demonstrating the need for more temporal data. We hope that the proposed dataset of temporal categories will help guide future research in temporal modeling for better video understanding.
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
Ucf101: 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
SlowFast Networks for Video Recognition
Feichtenhofer, C., Fan, H., Malik, J., & He, K. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00630 · Cited by 4,007
Hmdb: a large video database for human motion recognition
Kuehne, H., Jhuang, H., Garrote, E., Poggio, T., & Serre, T. (2011) · 2011 International Conference on Computer Vision · doi:10.1109/iccv.2011.6126543 · Cited by 3,965
A Closer Look at Spatiotemporal Convolutions for Action Recognition
Tran, D., Wang, H., Torresani, L., Ray, J., LeCun, Y., & Paluri, M. (2017) · arXiv · doi:10.48550/arxiv.1711.11248 · Cited by 3,664 · cited 3×
“ludes convolutions in the temporal dimension; I3D [2] which is also a 3D architecture, that extends inception to use convolutions in the temporal dimension; and R(2+1)D which is a recent architecture [29] that achieves state-of-the-art accuracy. The main difference compared to R3D is that R(2+1)D factors the 3D convol…”
BackgroundMethodInfluentialSelf-citationAn Experimental Study of Apparent Behavior
Heider, F., & Simmel, M. (1944) · The American Journal of Psychology · doi:10.2307/1416950 · Cited by 3,340
ActivityNet: A large-scale video benchmark for human activity understanding
Heilbron, F. C., Escorcia, V., Ghanem, B., & Niebles, J. C. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298698 · Cited by 2,578
Unsupervised Learning of Video Representations using LSTMs
Srivastava, N., Mansimov, E., & Salakhutdinov, R. (2015) · arXiv · doi:10.48550/arxiv.1502.04681 · Cited by 1,861
The “Something Something” Video Database for Learning and Evaluating Visual Common Sense
Goyal, R., Kahou, S. E., Michalski, V., Materzynska, J., Westphal, S., Kim, H., Haenel, V., Fruend, I., Yianilos, P., Mueller-Freitag, M., et al. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.622 · Cited by 1,471
Shuffle and Learn: Unsupervised Learning Using Temporal Order Verification
Misra, I., Zitnick, C. L., & Hebert, M. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-46448-0_32 · Cited by 779 · cited 2×
“From Kinetics: [18, 20, 23, 26, 53, 57, 80, 88, 91, 95, 99, 113, 126, 139, 181, 182, 183, 186, 200, 201, 210, 218, 226, 227, 255, 268, 298, 354, 366, 388, 397, 398] From Something-something: [9, 15, 42, 50, 58, 61, 63, 71, 78, 90, 93, 106, 109, 114, 121, 130, 138, 165]”
Cited by
Is Space-Time Attention All You Need for Video Understanding?
Bertasius, G., Wang, H., & Torresani, L. (2021) · arXiv · doi:10.48550/arxiv.2102.05095 · Cited by 1,663
Self-citationNeimark, D., Bar, O., Zohar, M., & Asselmann, D. (2021) · 2021 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW) · doi:10.1109/iccvw54120.2021.00355 · Cited by 551
“We also argue that this could mean that Kinetics-400 is primarily a static frame, appearance based classification problem rather than a motion problem [31].”
BackgroundRevisiting Temporal Modeling for CLIP-Based Image-to-Video Knowledge Transferring
Liu, R., Huang, J., Li, G., Feng, J., Wu, X., & Li, T. H. (2023) · 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52729.2023.00634 · Cited by 78
Frozen in Time: A Joint Video and Image Encoder for End-to-End Retrieval
Bain, M., Nagrani, A., Varol, G., & Zisserman, A. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00175 · Cited by 76
“For example, although classifying some human actions requires the temporal ordering of video frames, many actions can be classified from just their distribution over frames or even from a single frame [51].”
Background
Metadata
- Authors
- Sevilla-Lara, L., Zha, S., Yan, Z., Goswami, V., Feiszli, M., & Torresani, L.
- Venue
- 2021 IEEE Winter Conference on Applications of Computer Vision (WACV)
- Publisher
- IEEE
- Published
- 2021-01
- Pages
- 535-544
- ISSN
- 2472-6737 (ISSN-L)
- OpenAlex
- W2964111881
- Cited by
- 60
- References
- 11
- FWCI
- 3.98
- 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
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Only Time Can Tell: Discovering Temporal Data for Temporal Modeling. https://app.cochat.ai/papers/10.1109/wacv48630.2021.00058
- The paper
- Sevilla-Lara, L., Zha, S., Yan, Z., Goswami, V., Feiszli, M., & Torresani, L. (2021). Only Time Can Tell: Discovering Temporal Data for Temporal Modeling. 2021 IEEE Winter Conference on Applications of Computer Vision (WACV). https://doi.org/10.1109/wacv48630.2021.00058
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.