7 citations · 27 across the 29 of their papers we have counts for
19 papers · 1 filter
HiRAE: Hierarchical Representation Autoencoding with Residual Budgets
Xuanyu Zhu, Yan Bai, Yang Shi +5
Pretrained visual representations support image generation, but may not fully preserve the fine-grained details needed for faithful reconstruction. Meanwhile, intermediate encoder…
TUE-Detector: A Tool-Using Expert MLLM-Based Detector for AI-Generated Videos
Yichen Wu, Haoxuan Qu, Yongxing Dai +5
AI-generated video detection, which aims to distinguish AI-generated videos from real ones, has recently received increasing research attention. To perform this task reliably, a ke…
CANVAS: Consistency-Aware Navigation via Visual Adaptive Sampling for Long-Context Text-to-SVG Generation
Yichen Wu, Haoxuan Qu, Yihang Lou +2
Autoregressive large models have recently advanced Text-to-SVG generation from simple icons to complex, long-context graphics, yet standard autoregressive decoding often fails to m…
ToolFG: Towards Well-Grounded Fine-Grained Image Classification
Yu Xue, Haoxuan Qu, Zhuoling Li +4
Fine-grained image classification (FGIC) has broad applications and has attracted significant research attention. In this paper, we explore a novel paradigm for solving FGIC by pro…
OmniSelect: Dynamic Modality-Aware Token Compression for Efficient Omni-modal Large Language Models
Morunliu Yang, Ruotao Xu, Le Li +6
Omnimodal large language models (OmniLLMs) have recently gained increasing attention for unified audio-video understanding. However, processing long multimodal token sequences intr…
Beyond the Last Layer: Multi-Layer Representation Fusion for Visual Tokenization
Xuanyu Zhu, Yan Bai, Yang Shi +4
Representation autoencoders that reuse frozen pretrained vision encoders as visual tokenizers have achieved strong reconstruction and generation quality. However, existing methods…
MMVIAD: Multi-view Multi-task Video Understanding for Industrial Anomaly Detection
Xiran Zhao, Jing Jin, Yan Bai +6
Industrial anomaly detection is critical for manufacturing quality control, yet existing datasets mainly focus on static images or sparse views, which do not fully reflect continuo…
Unveiling Fine-Grained Visual Traces: Evaluating Multimodal Interleaved Reasoning Chains in Multimodal STEM Tasks
Jing Jin, Hao Liu, Yan Bai +9
Multimodal large language models (MLLMs) have shown promising reasoning abilities, yet evaluating their performance in specialized domains remains challenging. STEM reasoning is a…
Diagnosing and Repairing Unsafe Channels in Vision-Language Models via Causal Discovery and Dual-Modal Safety Subspace Projection
Jinhu Fu, Yihang Lou, Qingyi Si +3
Large Vision-Language Models (LVLMs) have achieved impressive performance across multimodal understanding and reasoning tasks, yet their internal safety mechanisms remain opaque an…
Decorate the Newcomers: Visual Domain Prompt for Continual Test Time Adaptation
Yulu Gan, Yan Bai, Yihang Lou +4
Continual Test-Time Adaptation (CTTA) aims to adapt the source model to continually changing unlabeled target domains without access to the source data. Existing methods mainly foc…
Memory-Based Label-Text Tuning for Few-Shot Class-Incremental Learning
Jinze Li, Yan Bai, Yihang Lou +4
Few-shot class-incremental learning(FSCIL) focuses on designing learning algorithms that can continually learn a sequence of new tasks from a few samples without forgetting old one…
Bayesian Evidential Learning for Few-Shot Classification
Xiongkun Linghu, Yan Bai, Yihang Lou +4
Few-Shot Classification(FSC) aims to generalize from base classes to novel classes given very limited labeled samples, which is an important step on the path toward human-like mach…
Dual-Tuning: Joint Prototype Transfer and Structure Regularization for Compatible Feature Learning
Yan Bai, Jile Jiao, Shengsen Wu +4
Visual retrieval system faces frequent model update and deployment. It is a heavy workload to re-extract features of the whole database every time.Feature compatibility enables the…
Neighborhood Consensus Contrastive Learning for Backward-Compatible Representation
Shengsen Wu, Liang Chen, Yihang Lou +4
In object re-identification (ReID), the development of deep learning techniques often involves model updates and deployment. It is unbearable to re-embedding and re-index with the…
Towards Digital Retina in Smart Cities: A Model Generation, Utilization and Communication Paradigm
Yihang Lou, Ling-Yu Duan, Yong Luo +4
The digital retina in smart cities is to select what the City Eye tells the City Brain, and convert the acquired visual data from front-end visual sensors to features in an intelli…
AI Oriented Large-Scale Video Management for Smart City: Technologies, Standards and Beyond
Lingyu Duan, Yihang Lou, Shiqi Wang +2
Deep learning has achieved substantial success in a series of tasks in computer vision. Intelligent video analysis, which can be broadly applied to video surveillance in various sm…
Compact Descriptors for Video Analysis: the Emerging MPEG Standard
Ling-Yu Duan, Vijay Chandrasekhar, Shiqi Wang +6
This paper provides an overview of the on-going compact descriptors for video analysis standard (CDVA) from the ISO/IEC moving pictures experts group (MPEG). MPEG-CDVA targets at d…
Improving Object Detection with Region Similarity Learning
Feng Gao, Yihang Lou, Yan Bai +3
Object detection aims to identify instances of semantic objects of a certain class in images or videos. The success of state-of-the-art approaches is attributed to the significant…
Incorporating Intra-Class Variance to Fine-Grained Visual Recognition
Yan Bai, Feng Gao, Yihang Lou +3
Fine-grained visual recognition aims to capture discriminative characteristics amongst visually similar categories. The state-of-the-art research work has significantly improved th…