conftrace_

Daiki Shimada

3 papers · 2025–2026 · 2 conferences · across top CS/AI conferences

Achievements

Jump to papers ↓

🌍 Conference Polyglot (2) 🧭 Keyword Pioneer 🐝 Cross-Pollinator (15)

Conferences

AAAI (2) ICLR (1)

Top co-authors

Chenliang Xu (3) Jing Bi (2) Hang Hua (2) Mingqian Feng (2) Susan Liang (2) Zeliang Zhang (2) Zhuo Liu (1) Junjia Guo (1) Yunlong Tang (1) Yizhi Song (1)

Keywords

video captioning (1) multimodal learning (1) object tracking (1) vision language model (1) multimodal language model (1) temporal coherence (1) video question answering (1) temporal localization (1) dense captioning (1) audio-visual understanding (1)

Papers

Caption Anything in Video: Fine-grained Object-centric Captioning via Spatiotemporal Multimodal Prompting AAAI 2026 Empowering LLMs with Pseudo-Untrimmed Videos for Audio-Visual Temporal Understanding AAAI 2025 Rethinking Audio-Visual Adversarial Vulnerability from Temporal and Modality Perspectives ICLR 2025