相关论文: Towards Mitigating Modality Bias in Vision-Languag…

Vision-Language-Action (VLA) models mark a transformative advancement in artificial intelligence, aiming to unify perception, natural language understanding, and embodied action within a single computational framework. This foundational…

Vision-Language Model (VLM) have gained widespread adoption in Open-Vocabulary (OV) object detection and segmentation tasks. Despite they have shown promise on OV-related tasks, their effectiveness in conventional vision tasks has thus far…

State of the art architectures for untrimmed video Temporal Action Localization (TAL) have only considered RGB and Flow modalities, leaving the information-rich audio modality totally unexploited. Audio fusion has been explored for the…

Vision Language Models (VLMs) excel in zero-shot image classification by pairing images with textual category names. The expanding variety of Pre-Trained VLMs enhances the likelihood of identifying a suitable VLM for specific tasks. To…

Vision-language models (VLMs) have achieved impressive performance across a wide range of multimodal tasks. However, they often fail on tasks that require fine-grained visual perception, even when the required information is still present…

Foundation models for vision have transformed visual recognition with powerful pretrained representations and strong zero-shot capabilities, yet their potential for data-efficient learning remains largely untapped. Active Learning (AL) aims…

Real-world videos often contain overlapping events and complex temporal dependencies, making multimodal interaction modeling particularly challenging. We introduce DEL, a framework for dense semantic action localization, aiming to…

The crux of semi-supervised temporal action localization (SS-TAL) lies in excavating valuable information from abundant unlabeled videos. However, current approaches predominantly focus on building models that are robust to the error-prone…

Latent Action Models (LAMs) enable Vision- Language-Action (VLA) systems to learn semantic action representations from large-scale unannotated data. Yet, we identify two bottlenecks of LAMs: 1) the commonly adopted end-to-end trained image…

With the ever-increasing popularity of pretrained Video-Language Models (VidLMs), there is a pressing need to develop robust evaluation methodologies that delve deeper into their visio-linguistic capabilities. To address this challenge, we…

Vision-language Models (VLMs), despite achieving strong performance on multimodal benchmarks, often misinterpret straightforward visual concepts that humans identify effortlessly, such as counting, spatial reasoning, and viewpoint…

Temporal Action Localization (TAL) aims to predict both action category and temporal boundary of action instances in untrimmed videos, i.e., start and end time. Fully-supervised solutions are usually adopted in most existing works, and…

Vision Language Models (VLMs) are designed to extend Large Language Models (LLMs) with visual capabilities, yet in this work we observe a surprising phenomenon: VLMs can outperform their underlying LLMs on purely text-only tasks,…

Contrastive decoding strategies are widely used to mitigate object hallucinations in multimodal large language models (MLLMs). By reducing over-reliance on language priors, these strategies ensure that generated content remains closely…

Vision-language models (VLMs) exhibit a systematic bias when confronted with classic optical illusions: they overwhelmingly predict the illusion as "real" regardless of whether the image has been counterfactually modified. We present a…

Effectively tackling the problem of temporal action localization (TAL) necessitates a visual representation that jointly pursues two confounding goals, i.e., fine-grained discrimination for temporal localization and sufficient visual…

Referring Video Object Segmentation (RVOS) aims to segment and track objects in videos based on natural language expressions, requiring precise alignment between visual content and textual queries. However, existing methods often suffer…

Point-supervised Temporal Action Localization (PTAL) adopts a lightly frame-annotated paradigm (\textit{i.e.}, labeling only a single frame per action instance) to train a model to effectively locate action instances within untrimmed…

Large Vision Language Models (VLMs) effectively bridge the modality gap through extensive pretraining, acquiring sophisticated visual representations aligned with language. However, it remains underexplored whether these representations,…

Defending pre-trained vision-language models (VLMs), such as CLIP, against adversarial attacks is crucial, as these models are widely used in diverse zero-shot tasks, including image classification. However, existing adversarial training…