相关论文: Scaling Video-Language Models to 10K Frames via Hi…

Vision-Language Models (VLMs) have shown remarkable performance on diverse visual and linguistic tasks, yet they remain fundamentally limited in their understanding of 3D spatial structures. We propose Geometric Distillation, a lightweight,…

In this paper, we introduce DetailCLIP: A Detail-Oriented CLIP to address the limitations of contrastive learning-based vision-language models, particularly CLIP, in handling detail-oriented and fine-grained tasks like segmentation. While…

A well-known dilemma in large vision-language models (e.g., GPT-4, LLaVA) is that while increasing the number of vision tokens generally enhances visual understanding, it also significantly raises memory and computational costs, especially…

Diffusion-based Video Super-Resolution (VSR) is renowned for generating perceptually realistic videos, yet it grapples with maintaining detail consistency across frames due to stochastic fluctuations. The traditional approach of pixel-level…

Reasoning is increasingly crucial for various tasks. While chain-of-thought prompting enables large language models to leverage reasoning effectively, harnessing the reasoning capabilities of Vision-Language Models (VLMs) remains…

Recent efforts in video reasoning segmentation (VRS) integrate large language models (LLMs) with perception models to localize and track objects via textual instructions, achieving barely satisfactory results in simple scenarios. However,…

Vision-Language Models (VLMs) have enabled substantial progress in video understanding by leveraging cross-modal reasoning capabilities. However, their effectiveness is limited by the restricted context window and the high computational…

Vision-Language Models (VLMs) are crucial for applications requiring integrated understanding textual and visual information. However, existing VLMs struggle with long videos due to computational inefficiency, memory limitations, and…

Multimodal large language models (MLLMs) improve performance on vision-language tasks by integrating visual features from pre-trained vision encoders into large language models (LLMs). However, how MLLMs process and utilize visual…

Large language models (LLMs) excel at retrieving information from lengthy text, but their vision-language counterparts (VLMs) face difficulties with hour-long videos, especially for temporal grounding. Specifically, these VLMs are…

Despite great progress, text-driven long video editing is still notoriously challenging mainly due to excessive memory overhead. Although recent efforts have simplified this task into a two-step process of keyframe translation and…

Video-based multimodal large language models (Video-LLMs) possess significant potential for video understanding tasks. However, most Video-LLMs treat videos as a sequential set of individual frames, which results in insufficient…

Rapid development of large language models (LLMs) has significantly advanced multimodal large language models (LMMs), particularly in vision-language tasks. However, existing video-language models often overlook precise temporal…

Multi-modal large language models (MLLMs) have demonstrated considerable potential across various downstream tasks that require cross-domain knowledge. MLLMs capable of processing videos, known as Video-MLLMs, have attracted broad interest…

Video Large Language Models (Video-LLMs) excel at understanding videos in-context, provided they have full access to the video when answering queries. However, these models face challenges in streaming scenarios where hour-long videos must…

We present Distill CLIP (DCLIP), a fine-tuned variant of the CLIP model that enhances multimodal image-text retrieval while preserving the original model's strong zero-shot classification capabilities. CLIP models are typically constrained…

Audio-visual video recognition (AVVR) aims to integrate audio and visual clues to categorize videos accurately. While existing methods train AVVR models using provided datasets and achieve satisfactory results, they struggle to retain…

Effectively applying Vision-Language Models (VLMs) to Video Question Answering (VideoQA) hinges on selecting a concise yet comprehensive set of frames, as processing entire videos is computationally infeasible. However, current frame…

Knowledge distillation offers a transformative pathway to developing powerful, yet efficient, small language models (SLMs) suitable for resource-constrained environments. In this paper, we benchmark the performance and computational cost of…

We propose DiffCLIP, a novel vision-language model that extends the differential attention mechanism to CLIP architectures. Differential attention was originally developed for large language models to amplify relevant context while…