6 papers
HumanScale: Egocentric Human Video Can Outperform Real-Robot Data for Embodied Pretraining
Juncheng Ma, Jianxin Bi, Yufan Deng +19
Embodied foundation models are expected to benefit from data scaling like large language models, but face a much tighter data bottleneck. Teleoperated real-robot trajectories remai…
VideoQA in the Era of LLMs: An Empirical Study
Junbin Xiao, Nanxin Huang, Hangyu Qin +8
Video Large Language Models (Video-LLMs) are flourishing and has advanced many video-language tasks. As a golden testbed, Video Question Answering (VideoQA) plays pivotal role in V…
Reinforcing Video Reasoning with Focused Thinking
Jisheng Dang, Jingze Wu, Teng Wang +6
Recent advancements in reinforcement learning, particularly through Group Relative Policy Optimization (GRPO), have significantly improved multimodal large language models for comp…
Scene-Text Grounding for Text-Based Video Question Answering
Sheng Zhou, Junbin Xiao, Xun Yang +5
Existing efforts in text-based video question answering (TextVideoQA) are criticized for their opaque decisionmaking and heavy reliance on scene-text recognition. In this paper, we…
EgoTextVQA: Towards Egocentric Scene-Text Aware Video Question Answering
Sheng Zhou, Junbin Xiao, Qingyun Li +6
We introduce EgoTextVQA, a novel and rigorously constructed benchmark for egocentric QA assistance involving scene text. EgoTextVQA contains 1.5K ego-view videos and 7K scene-text…
Attend and Enrich: Enhanced Visual Prompt for Zero-Shot Learning
Man Liu, Huihui Bai, Feng Li +4
Zero-shot learning (ZSL) endeavors to transfer knowledge from seen categories to recognize unseen categories, which mostly relies on the semantic-visual interactions between image…