相关论文: A Hybrid Co-Finetuning Approach for Visual Bug Det…

Recent algorithms in convolutional neural networks (CNN) considerably advance the fine-grained image classification, which aims to differentiate subtle differences among subordinate classes. However, previous studies have rarely focused on…

Unsupervised pixel-level video understanding remains challenging in real-world scenarios, where motion blur, occlusion, and fast object dynamics often cause temporal drift and flickering pseudo-labels.We propose VVitCutLER, an unsupervised…

Classifier-Free Guidance (CFG) has been a default technique in various visual generative models, yet it requires inference from both conditional and unconditional models during sampling. We propose to build visual models that are free from…

Accurate detection of obstacles in 3D is an essential task for autonomous driving and intelligent transportation. In this work, we propose a general multimodal fusion framework FusionPainting to fuse the 2D RGB image and 3D point clouds at…

This paper introduces a novel self-learning framework that automates the label acquisition process for improving models for detecting players in broadcast footage of sports games. Unlike most previous self-learning approaches for improving…

Fine-tuning pre-trained large language models (LLMs) has become a common practice for personalized natural language understanding (NLU) applications on downstream tasks and domain-specific datasets. However, there are two main challenges:…

This paper presents a system for detecting fake audio-visual content (i.e., video deepfake), developed for Track 2 of the DDL Challenge. The proposed system employs a two-stage framework, comprising unimodal detection and multimodal score…

Source-Free Cross-Domain Few-Shot Learning (SF-CDFSL) focuses on fine-tuning with limited training data from target domains (e.g., medical or satellite images), where Vision-Language Models (VLMs) such as CLIP and SigLIP have shown…

Fine-Grained Visual Classification (FGVC) aims to categorize closely related subclasses, a task complicated by minimal inter-class differences and significant intra-class variance. Existing methods often rely on additional annotations for…

The rapid evolution of face manipulation techniques poses a critical challenge for face forgery detection: cross-domain generalization. Conventional methods, which rely on simple classification objectives, often fail to learn…

Camouflaged Object Detection (COD) is a critical aspect of computer vision aimed at identifying concealed objects, with applications spanning military, industrial, medical and monitoring domains. To address the problem of poor detail…

Robust feature representation plays significant role in visual tracking. However, it remains a challenging issue, since many factors may affect the experimental performance. The existing method which combine different features by setting…

In this paper, we propose a novel visual tracking framework that intelligently discovers reliable patterns from a wide range of video to resist drift error for long-term tracking tasks. First, we design a Discrete Fourier Transform (DFT)…

Fine-grained visual categorization (FGVC) aims to discriminate similar subcategories, whose main challenge is the large intraclass diversities and subtle inter-class differences. Existing FGVC methods usually select discriminant regions…

Prompt learning has become one of the most efficient paradigms for adapting large pre-trained vision-language models to downstream tasks. Current state-of-the-art methods, like CoOp and ProDA, tend to adopt soft prompts to learn an…

While supervised techniques in re-identification are extremely effective, the need for large amounts of annotations makes them impractical for large camera networks. One-shot re-identification, which uses a singular labeled tracklet for…

Machine learning has become an appealing signature-less approach to detect and classify malware because of its ability to generalize to never-before-seen samples and to handle large volumes of data. While traditional feature-based…

Multimodal visual information fusion aims to integrate the multi-sensor data into a single image which contains more complementary information and less redundant features. However the complementary information is hard to extract, especially…

Radars, due to their robustness to adverse weather conditions and ability to measure object motions, have served in autonomous driving and intelligent agents for years. However, Radar-based perception suffers from its unintuitive sensing…

Continual test-time adaptation aims to continuously adapt a pre-trained model to a stream of target domain data without accessing source data. Without access to source domain data, the model focuses solely on the feature characteristics of…