19 citations · 80 across the 40 of their papers we have counts for
41 papers
Reasoning Matters for 3D Visual Grounding
Hsiang-Wei Huang, Kuang-Ming Chen, Wenhao Chai +3
The recent development of Large Language Models (LLMs) with strong reasoning ability has driven research in various domains such as mathematics, coding, and scientific discovery. M…
UniHPR: Unified Human Pose Representation via Singular Value Contrastive Learning
Zhongyu Jiang, Wenhao Chai, Lei Li +3
In recent years, there has been a growing interest in developing effective alignment pipelines to generate unified representations from different modalities for multi-modal fusion…
ToSA: Token Merging with Spatial Awareness
Hsiang-Wei Huang, Wenhao Chai, Kuang-Ming Chen +2
Token merging has emerged as an effective strategy to accelerate Vision Transformers (ViT) by reducing computational costs. However, existing methods primarily rely on the visual t…
TEMPURA: Temporal Event Masked Prediction and Understanding for Reasoning in Action
Jen-Hao Cheng, Vivian Wang, Huayu Wang +11
Understanding causal event relationships and achieving fine-grained temporal grounding in videos remain challenging for vision-language models (VLMs). We propose TEMPURA (Temporal…
Video-MMLU: A Massive Multi-Discipline Lecture Understanding Benchmark
Enxin Song, Wenhao Chai, Weili Xu +3
Recent advancements in language multimodal models (LMMs) for video have demonstrated their potential for understanding video content, yet the task of comprehending multi-discipline…
EMMOE: A Comprehensive Benchmark for Embodied Mobile Manipulation in Open Environments
Dongping Li, Tielong Cai, Tianci Tang +3
Developing autonomous home robots controlled by natural language has long been a pursuit of humanity. While advancements in large language models (LLMs) and embodied intelligence m…
Pointmap Association and Piecewise-Plane Constraint for Consistent and Compact 3D Gaussian Segmentation Field
Wenhao Hu, Wenhao Chai, Shengyu Hao +4
Achieving a consistent and compact 3D segmentation field is crucial for maintaining semantic coherence across views and accurately representing scene structures. Previous 3D scene…
PackDiT: Joint Human Motion and Text Generation via Mutual Prompting
Zhongyu Jiang, Wenhao Chai, Zhuoran Zhou +3
Human motion generation has advanced markedly with the advent of diffusion models. Most recent studies have concentrated on generating motion sequences based on text prompts, commo…
SAMURAI: Adapting Segment Anything Model for Zero-Shot Visual Tracking with Motion-Aware Memory
Cheng-Yen Yang, Hsiang-Wei Huang, Wenhao Chai +2
The Segment Anything Model 2 (SAM 2) has demonstrated strong performance in object segmentation tasks but faces challenges in visual object tracking, particularly when managing cro…
LLaVA-Ultra: Large Chinese Language and Vision Assistant for Ultrasound
Xuechen Guo, Wenhao Chai, Shi-Yan Li +1
Multimodal Large Language Model (MLLM) has recently garnered attention as a prominent research focus. By harnessing powerful LLM, it facilitates a transition of conversational gene…
Ego3DT: Tracking Every 3D Object in Ego-centric Videos
Shengyu Hao, Wenhao Chai, Zhonghan Zhao +8
The growing interest in embodied intelligence has brought ego-centric perspectives to contemporary research. One significant challenge within this realm is the accurate localizatio…
Boosting Online 3D Multi-Object Tracking through Camera-Radar Cross Check
Sheng-Yao Kuan, Jen-Hao Cheng, Hsiang-Wei Huang +6
In the domain of autonomous driving, the integration of multi-modal perception techniques based on data from diverse sensors has demonstrated substantial progress. Effectively surp…
RT-Pose: A 4D Radar Tensor-based 3D Human Pose Estimation and Localization Benchmark
Yuan-Hao Ho, Jen-Hao Cheng, Sheng Yao Kuan +5
Traditional methods for human localization and pose estimation (HPE), which mainly rely on RGB images as an input modality, confront substantial limitations in real-world applicati…
STEVE Series: Step-by-Step Construction of Agent Systems in Minecraft
Zhonghan Zhao, Wenhao Chai, Xuan Wang +7
Building an embodied agent system with a large language model (LLM) as its core is a promising direction. Due to the significant costs and uncontrollable factors associated with de…
CityCraft: A Real Crafter for 3D City Generation
Jie Deng, Wenhao Chai, Junsheng Huang +9
City scene generation has gained significant attention in autonomous driving, smart city development, and traffic simulation. It helps enhance infrastructure planning and monitorin…
MovieChat+: Question-aware Sparse Memory for Long Video Question Answering
Enxin Song, Wenhao Chai, Tian Ye +3
Recently, integrating video foundation models and large language models to build a video understanding system can overcome the limitations of specific pre-defined vision tasks. Yet…
Do We Really Need a Complex Agent System? Distill Embodied Agent into a Single Model
Zhonghan Zhao, Ke Ma, Wenhao Chai +6
With the power of large language models (LLMs), open-ended embodied agents can flexibly understand human instructions, generate interpretable guidance strategies, and output execut…
MonoTAKD: Teaching Assistant Knowledge Distillation for Monocular 3D Object Detection
Hou-I Liu, Christine Wu, Jen-Hao Cheng +8
Monocular 3D object detection (Mono3D) holds noteworthy promise for autonomous driving applications owing to the cost-effectiveness and rich visual context of monocular camera sens…
VersaT2I: Improving Text-to-Image Models with Versatile Reward
Jianshu Guo, Wenhao Chai, Jie Deng +6
Recent text-to-image (T2I) models have benefited from large-scale and high-quality data, demonstrating impressive performance. However, these T2I models still struggle to produce i…
Hierarchical Auto-Organizing System for Open-Ended Multi-Agent Navigation
Zhonghan Zhao, Kewei Chen, Dongxu Guo +4
Due to the dynamic and unpredictable open-world setting, navigating complex environments in Minecraft poses significant challenges for multi-agent systems. Agents must interact wit…
MambaMOT: State-Space Model as Motion Predictor for Multi-Object Tracking
Hsiang-Wei Huang, Cheng-Yen Yang, Wenhao Chai +2
In the field of multi-object tracking (MOT), traditional methods often rely on the Kalman filter for motion prediction, leveraging its strengths in linear motion scenarios. However…
User-Aware Prefix-Tuning is a Good Learner for Personalized Image Captioning
Xuan Wang, Guanhong Wang, Wenhao Chai +2
Image captioning bridges the gap between vision and language by automatically generating natural language descriptions for images. Traditional image captioning methods often overlo…
CityGen: Infinite and Controllable City Layout Generation
Jie Deng, Wenhao Chai, Jianshu Guo +6
The recent surge in interest in city layout generation underscores its significance in urban planning and smart city development. The task involves procedurally or automatically ge…
UniHPE: Towards Unified Human Pose Estimation via Contrastive Learning
Zhongyu Jiang, Wenhao Chai, Lei Li +3
In recent times, there has been a growing interest in developing effective perception techniques for combining information from multiple modalities. This involves aligning features…