SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2501.02504 · AAAI · 2025

Watch Video, Catch Keyword: Context-aware Keyword Attention for Moment Retrieval and Highlight Detection

Jung Kim, Sangmin Lee, Dongjin Kim, Sung Um

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 10 functions out of this paper's own repositories and ran 8 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

RepositoryRoleRan
visualaikhu/keyword-detr — 8 of 10
FunctionStatusWhere it lives
FINCH Ran visualaikhu/keyword-detr/keyword_detr/keyword_attention.py
pointer only (licence: NONE) · get_code("a5491be770764e99")
clust_rank Ran visualaikhu/keyword-detr/keyword_detr/keyword_attention.py
pointer only (licence: NONE) · get_code("5bd0c943cf39930a")
connected_components Ran visualaikhu/keyword-detr/keyword_detr/keyword_attention.py
pointer only (licence: NONE) · get_code("a01b4dae82c605b3")
cool_mean Ran visualaikhu/keyword-detr/keyword_detr/keyword_attention.py
pointer only (licence: NONE) · get_code("6d57d0d9f47ab9ac")
get_clust Ran visualaikhu/keyword-detr/keyword_detr/keyword_attention.py
pointer only (licence: NONE) · get_code("4fdea7107027864f")
get_merge Ran visualaikhu/keyword-detr/keyword_detr/keyword_attention.py
pointer only (licence: NONE) · get_code("56c72fe8bbeadae8")
pairwise_distances Ran visualaikhu/keyword-detr/keyword_detr/keyword_attention.py
pointer only (licence: NONE) · get_code("732d646a00f52bf8")
req_numclust Ran visualaikhu/keyword-detr/keyword_detr/keyword_attention.py
pointer only (licence: NONE) · get_code("6abe6f21a2d60d53")
KeywordWeighting Not yet run visualaikhu/keyword-detr/keyword_detr/keyword_attention.py
pointer only (licence: NONE) · get_code("8dd53619c5c0df78")
update_adj Not yet run visualaikhu/keyword-detr/keyword_detr/keyword_attention.py
pointer only (licence: NONE) · get_code("3e1ae56847475e08")

Repositories linked to this paper

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

Abstract

The goal of video moment retrieval and highlight detection is to identify specific segments and highlights based on a given text query. With the rapid growth of video content and the overlap between these tasks, recent works have addressed both simultaneously. However, they still struggle to fully capture the overall video context, making it challenging to determine which words are most relevant. In this paper, we present a novel Video Context-aware Keyword Attention module that overcomes this limitation by capturing keyword variation within the context of the entire video. To achieve this, we introduce a video context clustering module that provides concise representations of the overall video context, thereby enhancing the understanding of keyword dynamics. Furthermore, we propose a keyword weight detection module with keyword-aware contrastive learning that incorporates keyword information to enhance fine-grained alignment between visual and textual features. Extensive experiments on the QVHighlights, TVSum, and Charades-STA benchmarks demonstrate that our proposed method significantly improves performance in moment retrieval and highlight detection tasks compared to existing approaches.

For agents

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

get_harvested_code_for_paper("2501.02504")
get_code_for_paper("2501.02504")
have("2501.02504")

Connect an agent — have() is free.