3 papers
cs.CV2025
TextVidBench: A Benchmark for Long Video Scene Text Understanding
Yangyang Zhong, Ji Qi, Yuan Yao +5
Despite recent progress on the short-video Text-Visual Question Answering (ViteVQA) task - largely driven by benchmarks such as M4-ViteVQA - existing datasets still suffer from lim…
cs.CV2025
ALTo: Adaptive-Length Tokenizer for Autoregressive Mask Generation
Lingfeng Wang, Hualing Lin, Senda Chen +5
While humans effortlessly draw visual objects and shapes by adaptively allocating attention based on their complexity, existing multimodal large language models (MLLMs) remain cons…
cs.CV2025
Adept: Annotation-Denoising Auxiliary Tasks with Discrete Cosine Transform Map and Keypoint for Human-Centric Pretraining
Weizhen He, Yunfeng Yan, Shixiang Tang +4
Human-centric perception is the core of diverse computer vision tasks and has been a long-standing research focus. However, previous research studied these human-centric tasks indi…