209 citations · 494 across the 26 of their papers we have counts for
26 papers
Exploring Multi-Modal Contextual Knowledge for Open-Vocabulary Object Detection
Yifan Xu, Mengdan Zhang, Xiaoshan Yang +1
In this paper, we for the first time explore helpful multi-modal contextual knowledge to understand novel categories for open-vocabulary object detection (OVD). The multi-modal con…
Multimodal Imbalance-Aware Gradient Modulation for Weakly-supervised Audio-Visual Video Parsing
Jie Fu, Junyu Gao, Changsheng Xu
Weakly-supervised audio-visual video parsing (WS-AVVP) aims to localize the temporal extents of audio, visual and audio-visual event instances as well as identify the corresponding…
MF-CLIP: Leveraging CLIP as Surrogate Models for No-box Adversarial Attacks
Jiaming Zhang, Lingyu Qiu, Qi Yi +4
The vulnerability of Deep Neural Networks (DNNs) to adversarial attacks poses a significant challenge to their deployment in safety-critical applications. While extensive research…
Camera-Incremental Object Re-Identification with Identity Knowledge Evolution
Hantao Yao, Lu Yu, Jifei Luo +1
Object Re-identification (ReID) aims to retrieve the probe object from many gallery images with the ReID model inferred based on a stationary camera-free dataset by associating and…
Multi-modal Queried Object Detection in the Wild
Yifan Xu, Mengdan Zhang, Chaoyou Fu +4
We introduce MQ-Det, an efficient architecture and pre-training strategy design to utilize both textual description with open-set generalization and visual exemplars with rich desc…
ProSpect: Prompt Spectrum for Attribute-Aware Personalization of Diffusion Models
Yuxin Zhang, Weiming Dong, Fan Tang +6
Personalizing generative models offers a way to guide image generation with user-provided references. Current personalization methods can invert an object or concept into the textu…
CLIP-VG: Self-paced Curriculum Adapting of CLIP for Visual Grounding
Linhui Xiao, Xiaoshan Yang, Fang Peng +3
Visual Grounding (VG) is a crucial topic in the field of vision and language, which involves locating a specific region described by expressions within an image. To reduce the reli…
Visual-Language Prompt Tuning with Knowledge-guided Context Optimization
Hantao Yao, Rui Zhang, Changsheng Xu
Prompt tuning is an effective way to adapt the pre-trained visual-language model (VLM) to the downstream task using task-related textual tokens. Representative CoOp-based work comb…
A Unified Arbitrary Style Transfer Framework via Adaptive Contrastive Learning
Yuxin Zhang, Fan Tang, Weiming Dong +4
We present Unified Contrastive Arbitrary Style Transfer (UCAST), a novel style representation learning and transfer framework, which can fit in most existing arbitrary image style…
Region-Aware Diffusion for Zero-shot Text-driven Image Editing
Nisha Huang, Fan Tang, Weiming Dong +2
Image manipulation under the guidance of textual descriptions has recently received a broad range of attention. In this study, we focus on the regional editing of images with the g…
GALIP: Generative Adversarial CLIPs for Text-to-Image Synthesis
Ming Tao, Bing-Kun Bao, Hao Tang +1
Synthesizing high-fidelity complex images from text is challenging. Based on large pretraining, the autoregressive and diffusion models can synthesize photo-realistic images. Altho…
Unlearnable Clusters: Towards Label-agnostic Unlearnable Examples
Jiaming Zhang, Xingjun Ma, Qi Yi +4
There is a growing interest in developing unlearnable examples (UEs) against visual privacy leaks on the Internet. UEs are training samples added with invisible but unlearnable noi…
SgVA-CLIP: Semantic-guided Visual Adapting of Vision-Language Models for Few-shot Image Classification
Fang Peng, Xiaoshan Yang, Linhui Xiao +2
Although significant progress has been made in few-shot learning, most of existing few-shot image classification methods require supervised pre-training on a large amount of sample…
Inversion-Based Style Transfer with Diffusion Models
Yuxin Zhang, Nisha Huang, Fan Tang +4
The artistic style within a painting is the means of expression, which includes not only the painting material, colors, and brushstrokes, but also the high-level attributes includi…
DiffStyler: Controllable Dual Diffusion for Text-Driven Image Stylization
Nisha Huang, Yuxin Zhang, Fan Tang +5
Despite the impressive results of arbitrary image-guided style transfer methods, text-driven image stylization has recently been proposed for transferring a natural image into a st…
Understanding and Mitigating Overfitting in Prompt Tuning for Vision-Language Models
Chengcheng Ma, Yang Liu, Jiankang Deng +3
Pretrained vision-language models (VLMs) such as CLIP have shown impressive generalization capability in downstream vision tasks with appropriate text prompts. Instead of designing…
Draw Your Art Dream: Diverse Digital Art Synthesis with Multimodal Guided Diffusion
Nisha Huang, Fan Tang, Weiming Dong +1
Digital art synthesis is receiving increasing attention in the multimedia community because of engaging the public with art effectively. Current digital art synthesis methods usual…
Domain Enhanced Arbitrary Image Style Transfer via Contrastive Learning
Yuxin Zhang, Fan Tang, Weiming Dong +4
In this work, we tackle the challenging problem of arbitrary image style transfer using a novel style feature representation learning method. A suitable style representation, as a…
Learning Muti-expert Distribution Calibration for Long-tailed Video Classification
Yufan Hu, Junyu Gao, Changsheng Xu
Most existing state-of-the-art video classification methods assume that the training data obey a uniform distribution. However, video data in the real world typically exhibit an im…
Learning Commonsense-aware Moment-Text Alignment for Fast Video Temporal Grounding
Ziyue Wu, Junyu Gao, Shucheng Huang +1
Grounding temporal video segments described in natural language queries effectively and efficiently is a crucial capability needed in vision-and-language fields. In this paper, we…
MGDCF: Distance Learning via Markov Graph Diffusion for Neural Collaborative Filtering
Jun Hu, Bryan Hooi, Shengsheng Qian +2
Graph Neural Networks (GNNs) have recently been utilized to build Collaborative Filtering (CF) models to predict user preferences based on historical user-item interactions. Howeve…
Fine-grained Temporal Contrastive Learning for Weakly-supervised Temporal Action Localization
Junyu Gao, Mengyuan Chen, Changsheng Xu
We target at the task of weakly-supervised action localization (WSAL), where only video-level action labels are available during model training. Despite the recent progress, existi…
CrossRectify: Leveraging Disagreement for Semi-supervised Object Detection
Chengcheng Ma, Xingjia Pan, Qixiang Ye +3
Semi-supervised object detection has recently achieved substantial progress. As a mainstream solution, the self-labeling-based methods train the detector on both labeled data and u…
Evo-ViT: Slow-Fast Token Evolution for Dynamic Vision Transformer
Yifan Xu, Zhijie Zhang, Mengdan Zhang +6
Vision transformers (ViTs) have recently received explosive popularity, but the huge computational cost is still a severe issue. Since the computation complexity of ViT is quadrati…