Related papers: Visual Prompt Multi-Modal Tracking

Combining traditional RGB cameras with bio-inspired event cameras for robust object tracking has garnered increasing attention in recent years. However, most existing multimodal tracking algorithms depend heavily on high-complexity Vision…

Pre-trained vision-language models are able to interpret visual concepts and language semantics. Prompt learning, a method of constructing prompts for text encoders or image encoders, elicits the potentials of pre-trained models and readily…

Adapting pre-trained models to open classes is a challenging problem in machine learning. Vision-language models fully explore the knowledge of text modality, demonstrating strong zero-shot recognition performance, which is naturally suited…

How to effectively exploit spatio-temporal information is crucial to capture target appearance changes in visual tracking. However, most deep learning-based trackers mainly focus on designing a complicated appearance model or template…

Recent vision-language models are driven by large-scale pretrained models. However, adapting pretrained models on limited data presents challenges such as overfitting, catastrophic forgetting, and the cross-modal gap between vision and…

There has been growing interest in parameter-efficient methods to apply pre-trained language models to downstream tasks. Building on the Prompt Tuning approach of Lester et al. (2021), which learns task-specific soft prompts to condition a…

As the scale of vision models continues to grow, the emergence of Visual Prompt Tuning (VPT) as a parameter-efficient transfer learning technique has gained attention due to its superior performance compared to traditional full-finetuning.…

The task of RGBT tracking aims to take the complementary advantages from visible spectrum and thermal infrared data to achieve robust visual tracking, and receives more and more attention in recent years. Existing works focus on…

Visual prompt tuning offers significant advantages for adapting pre-trained visual foundation models to specific tasks. However, current research provides limited insight into the interpretability of this approach, which is essential for…

Prompt learning has become a dominant paradigm for adapting vision-language models (VLMs) such as CLIP to downstream tasks without modifying pretrained weights. While extending prompts to both vision and text encoders across multiple…

Multimodal contrastive learning models (e.g., CLIP) can learn high-quality representations from large-scale image-text datasets, while they exhibit significant vulnerabilities to backdoor attacks, raising serious safety concerns. In this…

Open-world object counting leverages the robust text-image alignment of pre-trained vision-language models (VLMs) to enable counting of arbitrary categories in images specified by textual queries. However, widely adopted naive fine-tuning…

Visual Prompt Tuning (VPT) of pre-trained Vision Transformers (ViTs) has proven highly effective as a parameter-efficient fine-tuning technique for adapting large models to downstream tasks with limited data. Its parameter efficiency makes…

Various stuff and things in visual data possess specific traits, which can be learned by deep neural networks and are implicitly represented as the visual prior, e.g., object location and shape, in the model. Such prior potentially impacts…

Pre-trained point cloud models have found extensive applications in 3D understanding tasks like object classification and part segmentation. However, the prevailing strategy of full fine-tuning in downstream tasks leads to large per-task…

Referring understanding is a fundamental task that bridges natural language and visual content by localizing objects described in free-form expressions. However, existing works are constrained by limited language expressiveness, lacking the…

Few-shot, fine-grained classification in computer vision poses significant challenges due to the need to differentiate subtle class distinctions with limited data. This paper presents a novel method that enhances the Contrastive…

Multimodal sensing has proven valuable for visual tracking, as different sensor types offer unique strengths in handling one specific challenging scene where object appearance varies. While a generalist model capable of leveraging all…

In computer vision, Visual Prompting (VP) and Visual Prompt Tuning (VPT) have recently emerged as lightweight and effective alternatives to full fine-tuning for adapting large-scale vision models within the "pretrain-then-finetune"…

Visual transfer learning for unseen categories presents an active research topic yet a challenging task, due to the inherent conflict between preserving category-specific representations and acquiring transferable knowledge. Vision-Language…