3 citations · 6 across the 27 of their papers we have counts for
26 papers · 1 filter
EntropyScan: Towards Model-level Backdoor Detection in LVLMs via Visual Attention Entropy
Xuanyu Ge, Zhongqi Wang, Jie Zhang +2
Large Vision-Language Models (LVLMs) have demonstrated remarkable capabilities across various tasks, yet they remain vulnerable to backdoor attacks. Existing defense methods predom…
Component-Based Out-of-Distribution Detection
Wenrui Liu, Hong Chang, Ruibing Hou +2
Out-of-Distribution (OOD) detection requires sensitivity to subtle shifts without overreacting to natural In-Distribution (ID) diversity. However, from the viewpoint of detection g…
EgoMotion: Hierarchical Reasoning and Diffusion for Egocentric Vision-Language Motion Generation
Ruibing Hou, Mingyue Zhou, Yuwei Gui +5
Faithfully modeling human behavior in dynamic environments is a foundational challenge for embodied intelligence. While conditional motion synthesis has achieved significant advanc…
Revisiting Logit Distributions for Reliable Out-of-Distribution Detection
Jiachen Liang, Ruibing Hou, Minyang Hu +3
Out-of-distribution (OOD) detection is critical for ensuring the reliability of deep learning models in open-world applications. While post-hoc methods are favored for their effici…
MotionVerse: A Unified Multimodal Framework for Motion Comprehension, Generation and Editing
Ruibing Hou, Mingshuang Luo, Hongyu Pan +2
This paper proposes MotionVerse, a unified framework that harnesses the capabilities of Large Language Models (LLMs) to comprehend, generate, and edit human motion in both single-p…
GLip: A Global-Local Integrated Progressive Framework for Robust Visual Speech Recognition
Tianyue Wang, Shuang Yang, Shiguang Shan +1
Visual speech recognition (VSR), also known as lip reading, is the task of recognizing speech from silent video. Despite significant advancements in VSR over recent decades, most e…
HumanPCR: Probing MLLM Capabilities in Diverse Human-Centric Scenes
Keliang Li, Hongze Shen, Hao Shi +9
The aspiration for artificial general intelligence, fueled by the rapid progress of multimodal models, demands human-comparable performance across diverse environments. We propose…
unCLIP: Improving CLIP's Visual Detail Capturing Ability via Inverting unCLIP
Yinqi Li, Jiahe Zhao, Hong Chang +3
Contrastive Language-Image Pre-training (CLIP) has become a foundation model and has been applied to various vision and multimodal tasks. However, recent works indicate that CLIP f…
Jodi: Unification of Visual Generation and Understanding via Joint Modeling
Yifeng Xu, Zhenliang He, Meina Kan +2
Visual generation and understanding are two deeply interconnected aspects of human intelligence, yet they have been traditionally treated as separate tasks in machine learning. In…
DIVE: Inverting Conditional Diffusion Models for Discriminative Tasks
Yinqi Li, Hong Chang, Ruibing Hou +2
Diffusion models have shown remarkable progress in various generative tasks such as image and video generation. This paper studies the problem of leveraging pretrained diffusion mo…
HIS-GPT: Towards 3D Human-In-Scene Multimodal Understanding
Jiahe Zhao, Ruibing Hou, Zejie Tian +2
We propose a new task to benchmark human-in-scene understanding for embodied agents: Human-In-Scene Question Answering (HIS-QA). Given a human motion within a 3D scene, HIS-QA requ…
RefHCM: A Unified Model for Referring Perceptions in Human-Centric Scenarios
Jie Huang, Ruibing Hou, Jiahe Zhao +2
Human-centric perceptions play a crucial role in real-world applications. While recent human-centric works have achieved impressive progress, these efforts are often constrained to…
UMFC: Unsupervised Multi-Domain Feature Calibration for Vision-Language Models
Jiachen Liang, Ruibing Hou, Minyang Hu +3
Pre-trained vision-language models (e.g., CLIP) have shown powerful zero-shot transfer capabilities. But they still struggle with domain shifts and typically require labeled data t…
UniPose: A Unified Multimodal Framework for Human Pose Comprehension, Generation and Editing
Yiheng Li, Ruibing Hou, Hong Chang +2
Human pose plays a crucial role in the digital age. While recent works have achieved impressive progress in understanding and generating human poses, they often support only a sing…
HERM: Benchmarking and Enhancing Multimodal LLMs for Human-Centric Understanding
Keliang Li, Zaifei Yang, Jiahe Zhao +5
The significant advancements in visual understanding and instruction following from Multimodal Large Language Models (MLLMs) have opened up more possibilities for broader applicati…
CtrLoRA: An Extensible and Efficient Framework for Controllable Image Generation
Yifeng Xu, Zhenliang He, Shiguang Shan +1
Recently, large-scale diffusion models have made impressive progress in text-to-image (T2I) generation. To further equip these T2I models with fine-grained spatial control, approac…
Generalized Semi-Supervised Learning via Self-Supervised Feature Adaptation
Jiachen Liang, Ruibing Hou, Hong Chang +3
Traditional semi-supervised learning (SSL) assumes that the feature distributions of labeled and unlabeled data are consistent which rarely holds in realistic scenarios. In this pa…
Task-adaptive Q-Face
Haomiao Sun, Mingjie He, Shiguang Shan +2
Although face analysis has achieved remarkable improvements in the past few years, designing a multi-task face analysis model is still challenging. Most face analysis tasks are stu…
MGPT: An Advanced Multimodal, Multitask Framework for Motion Comprehension and Generation
Mingshuang Luo, Ruibing Hou, Zhuo Li +4
This paper presents MGPT, an advanced ultimodal, ultitask framework for otion comprehension and generation. MGPT operates on three funda…
HPNet: Dynamic Trajectory Forecasting with Historical Prediction Attention
Xiaolong Tang, Meina Kan, Shiguang Shan +3
Predicting the trajectories of road agents is essential for autonomous driving systems. The recent mainstream methods follow a static paradigm, which predicts the future trajectory…
GPT as Psychologist? Preliminary Evaluations for GPT-4V on Visual Affective Computing
Hao Lu, Xuesong Niu, Jiyao Wang +12
Multimodal large language models (MLLMs) are designed to process and integrate information from multiple sources, such as text, speech, images, and videos. Despite its success in l…
Clothes-Changing Person Re-Identification with Feasibility-Aware Intermediary Matching
Jiahe Zhao, Ruibing Hou, Hong Chang +4
Current clothes-changing person re-identification (re-id) approaches usually perform retrieval based on clothes-irrelevant features, while neglecting the potential of clothes-relev…
StylizedGS: Controllable Stylization for 3D Gaussian Splatting
Dingxi Zhang, Yu-Jie Yuan, Zhuoxun Chen +4
As XR technology continues to advance rapidly, 3D generation and editing are increasingly crucial. Among these, stylization plays a key role in enhancing the appearance of 3D model…
Task Attribute Distance for Few-Shot Learning: Theoretical Analysis and Applications
Minyang Hu, Hong Chang, Zong Guo +3
Few-shot learning (FSL) aims to learn novel tasks with very few labeled samples by leveraging experience from \emph{related} training tasks. In this paper, we try to understand FSL…