Papers › Technical Report: Temporal Aggregate Representations

Technical Report: Temporal Aggregate Representations

6 Jun 2021arXiv:2106.03152archive 2025-07-28

Fadime Sener, Dibyadip Chatterjee, Angela Yao

This technical report extends our work presented in [9] with more experiments. In [9], we tackle long-term video understanding, which requires reasoning from current and past or future observations and raises several fundamental questions. How should temporal or sequential relationships be modelled? What temporal extent of information and context needs to be processed? At what temporal scale should they be derived? [9] addresses these questions with a flexible multi-granular temporal aggregation framework. In this report, we conduct further experiments with this framework on different tasks and a new dataset, EPIC-KITCHENS-100.

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

dibschat/tempAgg officialmentioned in papermentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Rescaling Egocentric Vision (arXiv:2006.13256; that paper's own run record: 10 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 3 where Syntology's instrument failed) · 8 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 AnticipationAction RecognitionVideo Understanding

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Action Anticipation EPIC-KITCHENS-100 TempAgg Recall@5 14.73 #8 of 9 Archive leaderboard report
Action Anticipation EPIC-KITCHENS-100 (test) TempAgg recall@5 12.6 #5 of 8 Archive leaderboard report
Action Recognition EPIC-KITCHENS-100 TempAgg Action@1 45.26 #17 of 32 Archive leaderboard report
Action Recognition EPIC-KITCHENS-100 TempAgg Noun@1 53.35 #17 of 32 Archive leaderboard report
Action Recognition EPIC-KITCHENS-100 TempAgg Verb@1 66 #17 of 32 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