1 citations · 1 across the 17 of their papers we have counts for
20 papers
Traceable Human-to-Humanoid Sign Language Benchmarking
Ao Liu, Shengeng Tang, Lechao Cheng +3
Sign data collection is costly, and teleoperation scales poorly, motivating reuse of large video corpora. Humanoid signing requires converting video-derived human motion into robot…
Naturalness-guided Manifold Flow Matching for Sign Language Production
Jiayi He, Shengeng Tang, Sisi You +3
Sign Language Production (SLP) aims to generate sign motions from text. Conditional Flow Matching methods have achieved strong performance in SLP by constructing conditional paths…
Multi-Faceted Evaluation and Mitigation of Emotion Hallucinations in MLLMs
Bowen Zeng, Peipei Song, Weidong Chen +5
Multimodal large language models (MLLMs) have shown strong potential in open-ended emotion understanding, yet they often generate emotion hallucinations. Evaluating such hallucinat…
Rationale-Guided Knowledge Distillation for Cross-Lingual Stance Detection
Qiuli Zhou, Jingyuan Yao, Shengeng Tang +3
Stance detection aims to identify whether a text expresses a favorable or opposing attitude toward a given target, and serves as an important task for various downstream applicatio…
SoccerNet 2026 Challenges Results
Anthony Cioppa, Silvio Giancola, Håkan Ardö +102
The SoccerNet 2026 Challenges constitute the sixth annual edition of the SoccerNet open benchmarking effort, dedicated to advancing computer vision research in sports video underst…
Accelerating Controllable Generation via Hybrid-grained Cache
Lin Liu, Huixia Ben, Shuo Wang +4
Controllable generative models have been widely used to improve the realism of synthetic visual content. However, such models must handle control conditions and content generation…
SLRTP2025 Sign Language Production Challenge: Methodology, Results, and Future Work
Harry Walsh, Ed Fish, Ozge Mercanoglu Sincan +19
Sign Language Production (SLP) is the task of generating sign language video from spoken language inputs. The field has seen a range of innovations over the last few years, with th…
Motion is the Choreographer: Learning Latent Pose Dynamics for Seamless Sign Language Generation
Jiayi He, Xu Wang, Shengeng Tang +3
Sign language video generation requires producing natural signing motions with realistic appearances under precise semantic control, yet faces two critical challenges: excessive si…
Text2Lip: Progressive Lip-Synced Talking Face Generation from Text via Viseme-Guided Rendering
Xu Wang, Shengeng Tang, Fei Wang +4
Generating semantically coherent and visually accurate talking faces requires bridging the gap between linguistic meaning and facial articulation. Although audio-driven methods rem…
SplitGaussian: Reconstructing Dynamic Scenes via Visual Geometry Decomposition
Lechao Cheng, Jiahui Li, Jingxuan He +5
Reconstructing dynamic 3D scenes from monocular video remains fundamentally challenging due to the need to jointly infer motion, structure, and appearance from limited observations…
StgcDiff: Spatial-Temporal Graph Condition Diffusion for Sign Language Transition Generation
Jiashu He, Jiayi He, Shengeng Tang +3
Sign language transition generation seeks to convert discrete sign language segments into continuous sign videos by synthesizing smooth transitions. However,most existing methods m…
Towards Fine-Grained Emotion Understanding via Skeleton-Based Micro-Gesture Recognition
Hao Xu, Lechao Cheng, Yaxiong Wang +2
We present our solution to the MiGA Challenge at IJCAI 2025, which aims to recognize micro-gestures (MGs) from skeleton sequences for the purpose of hidden emotion understanding. M…
SignAligner: Harmonizing Complementary Pose Modalities for Coherent Sign Language Generation
Xu Wang, Shengeng Tang, Lechao Cheng +3
Sign language generation aims to produce diverse sign representations based on spoken language. However, achieving realistic and naturalistic generation remains a significant chall…
Wi-CBR: Salient-aware Adaptive WiFi Sensing for Cross-domain Behavior Recognition
Ruobei Zhang, Shengeng Tang, Huan Yan +2
The challenge in WiFi-based cross-domain Behavior Recognition lies in the significant interference of domain-specific signals on gesture variation. However, previous methods allevi…
EvEnhancer: Empowering Effectiveness, Efficiency and Generalizability for Continuous Space-Time Video Super-Resolution with Events
Shuoyan Wei, Feng Li, Shengeng Tang +2
Continuous space-time video super-resolution (C-STVSR) endeavors to upscale videos simultaneously at arbitrary spatial and temporal scales, which has recently garnered increasing i…
Text-Driven Diffusion Model for Sign Language Production
Jiayi He, Xu Wang, Ruobei Zhang +3
We introduce the hfut-lmc team's solution to the SLRTP Sign Production Challenge. The challenge aims to generate semantically aligned sign language pose sequences from text inputs.…
Knowledge Swapping via Learning and Unlearning
Mingyu Xing, Lechao Cheng, Shengeng Tang +3
We introduce \textbf{Knowledge Swapping}, a novel task designed to selectively regulate knowledge of a pretrained model by enabling the forgetting of user\-specified information, r…
Navigating Semantic Drift in Task-Agnostic Class-Incremental Learning
Fangwen Wu, Lechao Cheng, Shengeng Tang +4
Class-incremental learning (CIL) seeks to enable a model to sequentially learn new classes while retaining knowledge of previously learned ones. Balancing flexibility and stability…
Efficient Vision Language Model Fine-tuning for Text-based Person Anomaly Search
Jiayi He, Shengeng Tang, Ao Liu +3
This paper presents the HFUT-LMC team's solution to the WWW 2025 challenge on Text-based Person Anomaly Search (TPAS). The primary objective of this challenge is to accurately iden…
Discrete to Continuous: Generating Smooth Transition Poses from Sign Language Observation
Shengeng Tang, Jiayi He, Lechao Cheng +3
Generating continuous sign language videos from discrete segments is challenging due to the need for smooth transitions that preserve natural flow and meaning. Traditional approach…