7 accepted papers
Humans can robustly localize visual evidence and provide grounded answers even in noisy environments by identifying critical cues and then relating them to the full context in a bottom-up manner. Inspired by this, we propose DeepScan, a training-free framework that combines Hierarchical Scanning, Re
The emergence of 3D Gaussian Splatting (3DGS) has significantly advanced Novel View Synthesis (NVS) through explicit scene representation, enabling real-time photorealistic rendering. However, existing approaches manifest two critical limitations in complex scenarios: (1) Over-reconstruction occurs…
Despite the success of LVLMs, general optimization objectives (e.g., standard MLE) fail to constrain visual trajectories, leading to language bias and hallucination. To mitigate this, current methods introduce geometric priors from visual experts as additional supervision. However, we observe that s…
Most existing methods regard open-set Chinese text recognition (CTR) as a single-task problem, primarily focusing on prototype learning of linguistic components or glyphs to identify unseen characters. In contrast, humans identify characters by integrating multiple perspectives, including linguistic…
Existing visual token pruning methods target prompt alignment and visual preservation with static strategies, overlooking the varying relative importance of these objectives across tasks, which leads to inconsistent performance. To address this, we derive the first closed-form error bound for visual…
Scene text recognition is inherently a vision-language task. However, previous works have predominantly focused either on extracting more robust visual features or designing better language modeling. How to effectively and jointly model vision and language to mitigate heavy reliance on a single moda…
Humans often require only a few visual archetypes to spot novel objects. Based on this observation, we present a strategy rooted in ``spotting the unseen" by establishing dense correspondences between potential query image regions and a visual archetype, and we propose the Consensus Network (CoNet).…