SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2108.08121 · ICCV · 2021

Target Adaptive Context Aggregation for Video Scene Graph Generation

Zhifeng Li, Limin Wang, Gangshan Wu, Yao Teng

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

This paper deals with a challenging task of video scene graph generation (VidSGG), which could serve as a structured video representation for high-level understanding tasks. We present a new detect-to-track paradigm for this task by decoupling the context modeling for relation prediction from the complicated low-level entity tracking. Specifically, we design an efficient method for frame-level VidSGG, termed as Target Adaptive Context Aggregation Network (TRACE), with a focus on capturing spatio-temporal context information for relation recognition. Our TRACE framework streamlines the VidSGG pipeline with a modular design, and presents two unique blocks of Hierarchical Relation Tree (HRTree) construction and Target-adaptive Context Aggregation. More specific, our HRTree first provides an adpative structure for organizing possible relation candidates efficiently, and guides context aggregation module to effectively capture spatio-temporal structure information. Then, we obtain a contextualized feature representation for each relation candidate and build a classification head to recognize its relation category. Finally, we provide a simple temporal association strategy to track TRACE detected results to yield the video-level VidSGG. We perform experiments on two VidSGG benchmarks: ImageNet-VidVRD and Action Genome, and the results demonstrate that our TRACE achieves the state-of-the-art performance. The code and models are made available at https:// github.com/MCG-NJU/TRACE.

For agents

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

get_harvested_code_for_paper("2108.08121")
get_code_for_paper("2108.08121")
have("2108.08121")

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

curl https://syntology.ai/api/ran/2108.08121.json

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

[![Syntology run record](https://syntology.ai/api/ran/2108.08121.svg)](https://syntology.ai/paper/2108.08121)

Connect an agent — have() is free.