Papers › Revisiting Temporal Modeling for Video-based Person ReID

Revisiting Temporal Modeling for Video-based Person ReID

5 May 2018arXiv:1805.02104archive 2025-07-28

Jiyang Gao, Ram Nevatia

Video-based person reID is an important task, which has received much attention in recent years due to the increasing demand in surveillance and camera networks. A typical video-based person reID system consists of three parts: an image-level feature extractor (e.g. CNN), a temporal modeling method to aggregate temporal features and a loss function. Although many methods on temporal modeling have been proposed, it is hard to directly compare these methods, because the choice of feature extractor and loss function also have a large impact on the final performance. We comprehensively study and compare four different temporal modeling methods (temporal pooling, temporal attention, RNN and 3D convnets) for video-based person reID. We also propose a new attention generation network which adopts temporal convolution to extract temporal information among frames. The evaluation is done on the MARS dataset, and our methods outperform state-of-the-art methods by a large margin. Our source codes are released at https://github.com/jiyanggao/Video-Person-ReID.

PaperPDFCode

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

jiyanggao/Video-Person-ReID officialmentioned in papermentioned on GitHubpytorchSyntology: not harvested report
Allen-lz/Video-Person-ReID mentioned on GitHubpytorchSyntology: not harvested report
HoganZhang/Video-Person-ReID-temporal-modeling mentioned on GitHubpytorchSyntology: not harvested report
InnovArul/vidreid_cosegmentation mentioned on GitHubpytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Omni-Scale Feature Learning for Person Re-Identification (arXiv:1905.00953; that paper's own run record: 14 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 2 where Syntology's instrument failed) · 12 unverified); nothing checks that they implement this paper's method. report
Proxim123/person-re-id mentioned on GitHubpytorchSyntology: not harvested report
mattcoldwater/Video-ReID mentioned on GitHubpytorchSyntology: not harvested report
ppriyank/Video-Person-Re-ID-Fantastic-Techniques-and-Where-to-Find-Them mentioned on GitHubpytorchSyntology: not harvested report
pretendwh/Revisiting-temporal-modeling-for-video-based-person-reid mentioned on GitHubpytorchSyntology: not harvested 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.

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Convolution

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