相关论文: VidPrism: Heterogeneous Mixture of Experts for Ima…

Vision-Language Models (VLMs) based on Mixture-of-Experts (MoE) architectures have emerged as a pivotal paradigm in multimodal understanding, offering a powerful framework for integrating visual and linguistic information. However, the…

Joint understanding of video and language is an active research area with many applications. Prior work in this domain typically relies on learning text-video embeddings. One difficulty with this approach, however, is the lack of…

This study introduces an efficient and effective method, MeDM, that utilizes pre-trained image Diffusion Models for video-to-video translation with consistent temporal flow. The proposed framework can render videos from scene position…

Mixture-of-Experts (MoE) models embody the divide-and-conquer concept and are a promising approach for increasing model capacity, demonstrating excellent scalability across multiple domains. In this paper, we integrate the MoE structure…

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…

The core challenge in video understanding lies in perceiving dynamic content changes over time. However, multimodal large language models struggle with temporal-sensitive video tasks, which requires generating timestamps to mark the…

Video moment retrieval (VMR) is to search for a visual temporal moment in an untrimmed raw video by a given text query description (sentence). Existing studies either start from collecting exhaustive frame-wise annotations on the temporal…

Continual learning can empower vision-language models to continuously acquire new knowledge, without the need for access to the entire historical dataset. However, mitigating the performance degradation in large-scale models is non-trivial…

Knowledge Management is crucial for capturing and transferring expertise within universities, especially in high staff turnover contexts where expertise loss disrupts teaching. Documenting teachers' workflows is time-intensive and diverts…

The recent development of Video-based Large Language Models (VideoLLMs), has significantly advanced video summarization by aligning video features and, in some cases, audio features with Large Language Models (LLMs). Each of these VideoLLMs…

Seas of videos are uploaded daily with the popularity of social channels; thus, retrieving the most related video contents with user textual queries plays a more crucial role. Most methods consider only one joint embedding space between…

The visual medium (images and videos) naturally contains a large amount of information redundancy, thereby providing a great opportunity for leveraging efficiency in processing. While Vision Transformer (ViT) based models scale effectively…

We introduce VideoPrism, a general-purpose video encoder that tackles diverse video understanding tasks with a single frozen model. We pretrain VideoPrism on a heterogeneous corpus containing 36M high-quality video-caption pairs and 582M…

Visual place recognition (VPR) remains challenging due to significant viewpoint changes and appearance variations. Mainstream works tackle these challenges by developing various feature aggregation methods to transform deep features into…

Large-scale vision-language mixture-of-experts (VL-MoE) models provide strong multimodal capability, but efficient deployment on memory-constrained platforms remains difficult. Existing MoE offloading systems are largely designed for…

The field of natural language processing (NLP) has made significant strides in recent years, particularly in the development of large-scale vision-language models (VLMs). These models aim to bridge the gap between text and visual…

Long-form video understanding remains challenging for Vision-Language Models (VLMs) due to the inherent tension between computational constraints and the need to capture information distributed across thousands of frames. Existing…

With the exponential growth of user-generated content on video-sharing platforms, the challenge of facilitating efficient searching and browsing of videos has garnered significant attention. To enhance users' ability to swiftly locate and…

State-of-the-art video-text retrieval (VTR) methods typically involve fully fine-tuning a pre-trained model (e.g. CLIP) on specific datasets. However, this can result in significant storage costs in practical applications as a separate…

We present a unified Vision-Language pretrained Model (VLMo) that jointly learns a dual encoder and a fusion encoder with a modular Transformer network. Specifically, we introduce Mixture-of-Modality-Experts (MoME) Transformer, where each…