1 citations · 4 across the 15 of their papers we have counts for
13 papers · 1 filter
Messages, Not Tokens: Grounded Coresets for Faithful VLM Compression
Long Qian, Jiaqi Wei, Bingke Zhu +2
Modern vision language models (VLMs) turn high-resolution images into long sequences of visual tokens. Every token traverses the language decoder and persists in its prompt KV cach…
UniVAD v2: Unified Visual Anomaly Detection via Support-Conditioned Boundary Construction
Zhaopeng Gu, Bingke Zhu, Zhaowen Li +5
Unified visual anomaly detection seeks to train a single detector that can be deployed across categories, domains, and application scenarios. In the few-shot transfer regime, the k…
MUG: Pseudo Labeling Augmented Audio-Visual Mamba Network for Audio-Visual Video Parsing
Langyu Wang, Bingke Zhu, Yingying Chen +3
The weakly-supervised audio-visual video parsing (AVVP) aims to predict all modality-specific events and locate their temporal boundaries. Despite significant progress, due to the…
AnomalyMoE: Towards a Language-free Generalist Model for Unified Visual Anomaly Detection
Zhaopeng Gu, Bingke Zhu, Guibo Zhu +4
Anomaly detection is a critical task across numerous domains and modalities, yet existing methods are often highly specialized, limiting their generalizability. These specialized m…
Quality-Aware Language-Conditioned Local Auto-Regressive Anomaly Synthesis and Detection
Long Qian, Bingke Zhu, Yingying Chen +2
Despite substantial progress in anomaly synthesis methods, existing diffusion-based and coarse inpainting pipelines commonly suffer from structural deficiencies such as micro-struc…
MathPhys-Guided Coarse-to-Fine Anomaly Synthesis with SQE-Driven Bi-Level Optimization for Anomaly Detection
Long Qian, Bingke Zhu, Yingying Chen +2
Currently, industrial anomaly detection suffers from two bottlenecks: (i) the rarity of real-world defect images and (ii) the opacity of sample quality when synthetic data are used…
FiLo++: Zero-/Few-Shot Anomaly Detection by Fused Fine-Grained Descriptions and Deformable Localization
Zhaopeng Gu, Bingke Zhu, Guibo Zhu +3
Anomaly detection methods typically require extensive normal samples from the target class for training, limiting their applicability in scenarios that require rapid adaptation, su…
LINK: Adaptive Modality Interaction for Audio-Visual Video Parsing
Langyu Wang, Bingke Zhu, Yingying Chen +1
Audio-visual video parsing focuses on classifying videos through weak labels while identifying events as either visible, audible, or both, alongside their respective temporal bound…
UniVAD: A Training-free Unified Model for Few-shot Visual Anomaly Detection
Zhaopeng Gu, Bingke Zhu, Guibo Zhu +3
Visual Anomaly Detection (VAD) aims to identify abnormal samples in images that deviate from normal patterns, covering multiple domains, including industrial, logical, and medical…
The BRAVO Semantic Segmentation Challenge Results in UNCV2024
Tuan-Hung Vu, Eduardo Valle, Andrei Bursuc +16
We propose the unified BRAVO challenge to benchmark the reliability of semantic segmentation models under realistic perturbations and unknown out-of-distribution (OOD) scenarios. W…
MROVSeg: Breaking the Resolution Curse of Vision-Language Models in Open-Vocabulary Image Segmentation
Yuanbing Zhu, Bingke Zhu, Yingying Chen +3
Pretrained vision-language models (VLMs), \eg CLIP, are increasingly used to bridge the gap between open- and close-vocabulary recognition in open-vocabulary image segmentation. As…
FiLo: Zero-Shot Anomaly Detection by Fine-Grained Description and High-Quality Localization
Zhaopeng Gu, Bingke Zhu, Guibo Zhu +4
Zero-shot anomaly detection (ZSAD) methods entail detecting anomalies directly without access to any known normal or abnormal samples within the target item categories. Existing ap…
Optimization of Prompt Learning via Multi-Knowledge Representation for Vision-Language Models
Enming Zhang, Bingke Zhu, Yingying Chen +3
Vision-Language Models (VLMs), such as CLIP, play a foundational role in various cross-modal applications. To fully leverage VLMs' potential in adapting to downstream tasks, contex…