SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2408.09919 · ECCV · 2024

Long-Tail Temporal Action Segmentation with Group-wise Temporal Logit Adjustment

Angela Yao, Shrinivas Ramasubramanian, Fadime Sener, Zhanzhong Pang

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Procedural activity videos often exhibit a long-tailed action distribution due to varying action frequencies and durations. However, state-of-the-art temporal action segmentation methods overlook the long tail and fail to recognize tail actions. Existing long-tail methods make class-independent assumptions and struggle to identify tail classes when applied to temporal segmentation frameworks. This work proposes a novel group-wise temporal logit adjustment (G-TLA) framework that combines a group-wise softmax formulation while leveraging activity information and action ordering for logit adjustment. The proposed framework significantly improves in segmenting tail actions without any performance loss on head actions. Source code is available 4 .

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2408.09919")
get_code_for_paper("2408.09919")
have("2408.09919")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2408.09919.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2408.09919.svg)](https://syntology.ai/paper/2408.09919)

Connect an agent — have() is free.