ACCV
361 posts
@ACCVConf
The Official Account for the Asian Conference on Computer Vision (ACCV). #ACCV2026 Osaka.
Every Shot Counts... Now on ArXiv... sinhasaptarshi.github.io/escounts/ SOTA video repetition counting on RepCount, Countix and UCFRep. Code&Models Published Paper: arxiv.org/abs/2403.18074 Using exemplars during training, ESCounts learns a latent for exemplar-free, zero-shot inference.
Our #ACCV2024 Oral "LocoMotion: Learning Motion-Focused Video-Language Representations" w/ @fmthoker and @cgmsnoek is now on ArXiv arxiv.org/abs/2410.12018 We remove the spatial focus of video-language representations and instead train representations to have a motion focus.
Happy to share our second ACCV Oral: "Beyond Coarse-Grained Matching in Video-Text Retrieval" w/ Aozhu Chen, Xirong Li and @cgmsnoek arxiv.org/abs/2410.12407 We go beyond coarse-grained retrieval and explore whether models can discern subtle single-word differences in captions.
