Papers › Learning Video Representations from Correspondence Proposals

Learning Video Representations from Correspondence Proposals

20 May 2019CVPR 2019 6arXiv:1905.07853archive 2025-07-28

Xingyu Liu, Joon-Young Lee, Hailin Jin

Correspondences between frames encode rich information about dynamic content in videos. However, it is challenging to effectively capture and learn those due to their irregular structure and complex dynamics. In this paper, we propose a novel neural network that learns video representations by aggregating information from potential correspondences. This network, named CPNet, can learn evolving 2D fields with temporal consistency. In particular, it can effectively learn representations for videos by mixing appearance and long-range motion with an RGB-only input. We provide extensive ablation experiments to validate our model. CPNet shows stronger performance than existing methods on Kinetics and achieves the state-of-the-art performance on Something-Something and Jester. We provide analysis towards the behavior of our model and show its robustness to errors in proposals.

PaperPDFConference PDFCode

In Syntology View this paper on Syntology, its page in Syntology's graph. That page lists the repositories linked to the paper, the abstract and the calls for agents.

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

For agents, on Syntology's MCP service (how to connect):

Code

xingyul/cpnet officialmentioned on GitHubtfNOASSERTIONSyntology: not harvested report
xingyul/meteornet mentioned on GitHubtfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to MeteorNet: Deep Learning on Dynamic 3D Point Cloud Sequences (arXiv:1910.09165; that paper's own run record: 3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

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

Tasks

Action RecognitionAction Recognition In Videos

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Action Recognition In Videos Jester (Gesture Recognition) CPNet Res34, 5 CP Val 96.7 #1 of 9 Archive leaderboard report
Action Recognition In Videos Something-Something V2 CPNet Res34, 5 CP Top-1 Accuracy 57.65 #2 of 4 Archive leaderboard report
Action Recognition In Videos Something-Something V2 CPNet Res34, 5 CP Top-5 Accuracy 83.95 #2 of 4 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