Papers › Towards Universal Representation for Unseen Action Recognition

Towards Universal Representation for Unseen Action Recognition

22 Mar 2018CVPR 2018 6arXiv:1803.08460archive 2025-07-28

Yi Zhu, Yang Long, Yu Guan, Shawn Newsam, Ling Shao

Unseen Action Recognition (UAR) aims to recognise novel action categories without training examples. While previous methods focus on inner-dataset seen/unseen splits, this paper proposes a pipeline using a large-scale training source to achieve a Universal Representation (UR) that can generalise to a more realistic Cross-Dataset UAR (CD-UAR) scenario. We first address UAR as a Generalised Multiple-Instance Learning (GMIL) problem and discover 'building-blocks' from the large-scale ActivityNet dataset using distribution kernels. Essential visual and semantic components are preserved in a shared space to achieve the UR that can efficiently generalise to new datasets. Predicted UR exemplars can be improved by a simple semantic adaptation, and then an unseen action can be directly recognised using UR during the test. Without further training, extensive experiments manifest significant improvements over the UCF101 and HMDB51 benchmarks.

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 RecognitionMultiple Instance LearningTemporal Action LocalizationZero-Shot Action Recognition

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Action Recognition ActivityNet CD-UAR mAP 53.8 #15 of 16 Archive leaderboard report
Action Recognition HMDB-51 CD-UAR Average accuracy of 3 splits 51.8 #74 of 77 Archive leaderboard report
Action Recognition UCF101 CD-UAR 3-fold Accuracy 42.5 #87 of 91 Archive leaderboard report
Zero-Shot Action Recognition HMDB51 UR Top-1 Accuracy 24.4 #21 of 29 Archive leaderboard report
Zero-Shot Action Recognition UCF101 UR Top-1 Accuracy 17.5 #26 of 35 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