Junjia Guo

4 papers · 2025–2026 · 2 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌍 Conference Polyglot · Bronze 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (11) ❓ The Questioner

Venues

CVPR (3) AAAI (1)

Top co-authors

Chenliang Xu (4) Jing Bi (4) Susan Liang (3) Yunlong Tang (3) Chao Huang (3) Luchuan Song (2) Zeliang Zhang (2) Mingqian Feng (2) Hang Hua (2) Filippos Bellos (1)

Research topics

Artificial Intelligence (3) Core AI (3) Computer Vision (2) Deep Learning (2) Learning Types (2) Processing (2) Generation (1) Models (1) Techniques (1)

Keywords

multimodal large language model (2) multimodal learning (2) vision-language model (2) visual reasoning (1) visual grounding (1) object tracking (1) uncertainty estimation (1) attention head (1) decoding strategy (1) large vision-language model (1) temporal coherence (1) visual token (1) attention weight (1) visual understanding (1) large language model (1) video comprehension (1) video composition understanding (1) cinematic annotation (1) camera movement analysis (1) benchmark evaluation (1)

Papers

Caption Anything in Video: Fine-grained Object-centric Captioning via Spatiotemporal Multimodal Prompting AAAI 2026 When to Think and When to Look: Uncertainty-Guided Lookback CVPR 2026 Unveiling Visual Perception in Language Models: An Attention Head Analysis Approach CVPR 2025 VidComposition: Can MLLMs Analyze Compositions in Compiled Videos? CVPR 2025