15 citations · 15 across the 7 of their papers we have counts for
11 papers
Chart Deep Research in LVLMs via Parallel Relative Policy Optimization
Jiajin Tang, Gaoyang, Wenjie Wang +2
With the rapid advancement of data science, charts have evolved from simple numerical presentation tools to essential instruments for insight discovery and decision-making support.…
Augmenting Moment Retrieval: Zero-Dependency Two-Stage Learning
Zhengxuan Wei, Jiajin Tang, Sibei Yang
Existing Moment Retrieval methods face three critical bottlenecks: (1) data scarcity forces models into shallow keyword-feature associations; (2) boundary ambiguity in transition r…
Why LVLMs Are More Prone to Hallucinations in Longer Responses: The Role of Context
Ge Zheng, Jiaye Qian, Jiajin Tang +1
Large Vision-Language Models (LVLMs) have made significant progress in recent years but are also prone to hallucination issues. They exhibit more hallucinations in longer, free-for…
Closed-Loop Transfer for Weakly-supervised Affordance Grounding
Jiajin Tang, Zhengxuan Wei, Ge Zheng +1
Humans can perform previously unexperienced interactions with novel objects simply by observing others engage with them. Weakly-supervised affordance grounding mimics this process…
Sim-DETR: Unlock DETR for Temporal Sentence Grounding
Jiajin Tang, Zhengxuan Wei, Yuchen Zhu +4
Temporal sentence grounding aims to identify exact moments in a video that correspond to a given textual query, typically addressed with detection transformer (DETR) solutions. How…
Rethinking Query-based Transformer for Continual Image Segmentation
Yuchen Zhu, Cheng Shi, Dingyou Wang +5
Class-incremental/Continual image segmentation (CIS) aims to train an image segmenter in stages, where the set of available categories differs at each stage. To leverage the built-…
Part2Object: Hierarchical Unsupervised 3D Instance Segmentation
Cheng Shi, Yulin Zhang, Bin Yang +3
Unsupervised 3D instance segmentation aims to segment objects from a 3D point cloud without any annotations. Existing methods face the challenge of either too loose or too tight cl…
DDCoT: Duty-Distinct Chain-of-Thought Prompting for Multimodal Reasoning in Language Models
Ge Zheng, Bin Yang, Jiajin Tang +2
A long-standing goal of AI systems is to perform complex multimodal reasoning like humans. Recently, large language models (LLMs) have made remarkable strides in such multi-step re…
Temporal Collection and Distribution for Referring Video Object Segmentation
Jiajin Tang, Ge Zheng, Sibei Yang
Referring video object segmentation aims to segment a referent throughout a video sequence according to a natural language expression. It requires aligning the natural language exp…
CoTDet: Affordance Knowledge Prompting for Task Driven Object Detection
Jiajin Tang, Ge Zheng, Jingyi Yu +1
Task driven object detection aims to detect object instances suitable for affording a task in an image. Its challenge lies in object categories available for the task being too div…
Contrastive Grouping with Transformer for Referring Image Segmentation
Jiajin Tang, Ge Zheng, Cheng Shi +1
Referring image segmentation aims to segment the target referent in an image conditioning on a natural language expression. Existing one-stage methods employ per-pixel classificati…