2 citations · 5 across the 13 of their papers we have counts for
14 papers
TAME:Topology-Aware Text-Driven Motion Editing across Heterogeneous Humanoid Skeletons
Qichen Zheng, Siyuan Yang, Chong Wang +4
Text-driven motion editing modifies an existing motion sequence according to a text instruction while preserving the content of the source motion. Existing methods are typically bu…
Skeleton-to-Image Encoding: Enabling Skeleton Representation Learning via Vision-Pretrained Models
Siyuan Yang, Jun Liu, Hao Cheng +5
Recent advances in large-scale pretrained vision models have demonstrated impressive capabilities across a wide range of downstream tasks, including cross-modal and multi-modal sce…
Boosting SAM for Cross-Domain Few-Shot Segmentation via Conditional Point Sparsification
Jiahao Nie, Yun Xing, Wenbin An +6
Motivated by the success of the Segment Anything Model (SAM) in promptable segmentation, recent studies leverage SAM to develop training-free solutions for few-shot segmentation, w…
E.M.Ground: A Temporal Grounding Vid-LLM with Holistic Event Perception and Matching
Jiahao Nie, Wenbin An, Gongjie Zhang +4
Despite recent advances in Video Large Language Models (Vid-LLMs), Temporal Video Grounding (TVG), which aims to precisely localize time segments corresponding to query events, rem…
Cross-Domain Few-Shot Segmentation via Multi-view Progressive Adaptation
Jiahao Nie, Guanqiao Fu, Wenbin An +3
Cross-Domain Few-Shot Segmentation aims to segment categories in data-scarce domains conditioned on a few exemplars. Typical methods first establish few-shot capability in a large-…
MambaTAD: When State-Space Models Meet Long-Range Temporal Action Detection
Hui Lu, Yi Yu, Shijian Lu +4
Temporal Action Detection (TAD) aims to identify and localize actions by determining their starting and ending frames within untrimmed videos. Recent Structured State-Space Models…
MTL-UE: Learning to Learn Nothing for Multi-Task Learning
Yi Yu, Song Xia, Siyuan Yang +5
Most existing unlearnable strategies focus on preventing unauthorized users from training single-task learning (STL) models with personal data. Nevertheless, the paradigm has recen…
Towards Model Resistant to Transferable Adversarial Examples via Trigger Activation
Yi Yu, Song Xia, Xun Lin +5
Adversarial examples, characterized by imperceptible perturbations, pose significant threats to deep neural networks by misleading their predictions. A critical aspect of these exa…
Robust and Transferable Backdoor Attacks Against Deep Image Compression With Selective Frequency Prior
Yi Yu, Yufei Wang, Wenhan Yang +5
Recent advancements in deep learning-based compression techniques have surpassed traditional methods. However, deep neural networks remain vulnerable to backdoor attacks, where pre…
Backdoor Attacks against No-Reference Image Quality Assessment Models via a Scalable Trigger
Yi Yu, Song Xia, Xun Lin +4
No-Reference Image Quality Assessment (NR-IQA), responsible for assessing the quality of a single input image without using any reference, plays a critical role in evaluating and o…
Unlearnable Examples Detection via Iterative Filtering
Yi Yu, Qichen Zheng, Siyuan Yang +6
Deep neural networks are proven to be vulnerable to data poisoning attacks. Recently, a specific type of data poisoning attack known as availability attacks has led to the failure…
Mitigating Object Hallucinations in Large Vision-Language Models with Assembly of Global and Local Attention
Wenbin An, Feng Tian, Sicong Leng +6
Despite great success across various multimodal tasks, Large Vision-Language Models (LVLMs) often encounter object hallucinations with generated textual responses being inconsisten…
MMRel: Benchmarking Relation Understanding in Multi-Modal Large Language Models
Jiahao Nie, Gongjie Zhang, Wenbin An +4
Though Multi-modal Large Language Models (MLLMs) have recently achieved significant progress, they often struggle to understand diverse and complicated inter-object relations. Spec…
Purify Unlearnable Examples via Rate-Constrained Variational Autoencoders
Yi Yu, Yufei Wang, Song Xia +4
Unlearnable examples (UEs) seek to maximize testing error by making subtle modifications to training examples that are correctly labeled. Defenses against these poisoning attacks c…