Papers › Few-Shot Video Classification via Temporal Alignment

Few-Shot Video Classification via Temporal Alignment

27 Jun 2019CVPR 2020 6arXiv:1906.11415archive 2025-07-28

Kaidi Cao, Jingwei Ji, Zhangjie Cao, Chien-Yi Chang, Juan Carlos Niebles

There is a growing interest in learning a model which could recognize novel classes with only a few labeled examples. In this paper, we propose Temporal Alignment Module (TAM), a novel few-shot learning framework that can learn to classify a previous unseen video. While most previous works neglect long-term temporal ordering information, our proposed model explicitly leverages the temporal ordering information in video data through temporal alignment. This leads to strong data-efficiency for few-shot learning. In concrete, TAM calculates the distance value of query video with respect to novel class proxies by averaging the per frame distances along its alignment path. We introduce continuous relaxation to TAM so the model can be learned in an end-to-end fashion to directly optimize the few-shot learning objective. We evaluate TAM on two challenging real-world datasets, Kinetics and Something-Something-V2, and show that our model leads to significant improvement of few-shot video classification over a wide range of competitive baselines.

PaperPDFConference PDF

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Action RecognitionClassificationFew Shot Action RecognitionFew-Shot LearningGeneral ClassificationVideo Classification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Action Recognition Something-Something V2 TAM (5-shot) Top-1 Accuracy 52.3 #115 of 123 Archive leaderboard report
Few Shot Action Recognition Kinetics-100 OTAM Accuracy 85.8 #6 of 8 Archive leaderboard report
Few Shot Action Recognition Something-Something-100 OTAM 1:1 Accuracy 52.3 #5 of 5 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections