Jung Kim, Sangmin Lee, Dongjin Kim, Sung Um
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.
| Repository | Role | Ran |
|---|---|---|
| visualaikhu/keyword-detr | — | 8 of 10 |
| Function | Status | Where 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") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
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.
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.