相关论文: VIOLET : End-to-End Video-Language Transformers wi…

Large Multimodal Models (LMMs) often face a modality representation gap during pretraining: while language embeddings remain stable, visual representations are highly sensitive to contextual noise (e.g., background clutter). To address this…

Audio and video are two most common modalities in the mainstream media platforms, e.g., YouTube. To learn from multimodal videos effectively, in this work, we propose a novel audio-video recognition approach termed audio video Transformer,…

In recent years, large visual language models (LVLMs) have shown impressive performance and promising generalization capability in multi-modal tasks, thus replacing humans as receivers of visual information in various application scenarios.…

Multimodal embedding models have been crucial in enabling various downstream tasks such as semantic similarity, information retrieval, and clustering over different modalities. However, existing multimodal embeddings like VLM2Vec, E5-V, GME…

Vision-Language Pre-training (VLP) has advanced the performance of many vision-language tasks, such as image-text retrieval, visual entailment, and visual reasoning. The pre-training mostly utilizes lexical databases and image queries in…

Vision-and-Language Pre-training (VLP) has improved performance on various joint vision-and-language downstream tasks. Current approaches to VLP heavily rely on image feature extraction processes, most of which involve region supervision…

Masked video modeling~(MVM) has emerged as a highly effective pre-training strategy for visual foundation models, whereby the model reconstructs masked spatiotemporal tokens using information from visible tokens. However, a key challenge in…

We present a masked vision-language transformer (MVLT) for fashion-specific multi-modal representation. Technically, we simply utilize vision transformer architecture for replacing the BERT in the pre-training model, making MVLT the first…

Action recognition and localization in complex, untrimmed videos remain a formidable challenge in computer vision, largely due to the limitations of existing methods in capturing fine-grained actions, long-term temporal dependencies, and…

Encoding video content into compact latent tokens has become a fundamental step in video generation and understanding, driven by the need to address the inherent redundancy in pixel-level representations. Consequently, there is a growing…

Video paragraph captioning aims to generate a multi-sentence description of an untrimmed video with several temporal event locations in coherent storytelling. Following the human perception process, where the scene is effectively understood…

In this paper, we introduce $\text{EVL}_{\text{Gen}}$, a streamlined framework designed for the pre-training of visually conditioned language generation models with high computational demands, utilizing frozen pre-trained large language…

We present a simple yet effective end-to-end Video-language Pre-training (VidLP) framework, Masked Contrastive Video-language Pretraining (MAC), for video-text retrieval tasks. Our MAC aims to reduce video representation's spatial and…

Recent breakthroughs in vision-language models (VLMs) start a new page in the vision community. The VLMs provide stronger and more generalizable feature embeddings compared to those from ImageNet-pretrained models, thanks to the training on…

Contrastive pre-training on image-text pairs, exemplified by CLIP, becomes a standard technique for learning multi-modal visual-language representations. Although CLIP has demonstrated remarkable performance, training it from scratch on…

We propose the Vision-and-Augmented-Language Transformer (VAuLT). VAuLT is an extension of the popular Vision-and-Language Transformer (ViLT), and improves performance on vision-and-language (VL) tasks that involve more complex text inputs…

Video understanding relies on perceiving the global content and modeling its internal connections (e.g., causality, movement, and spatio-temporal correspondence). To learn these interactions, we apply a mask-then-predict pre-training task…

Token-based video representation has emerged as a promising approach for enabling large language models (LLMs) to interpret video content. However, existing token reduction techniques, such as pruning and merging, often disrupt essential…

We present \textsc{Vx2Text}, a framework for text generation from multimodal inputs consisting of video plus text, speech, or audio. In order to leverage transformer networks, which have been shown to be effective at modeling language, each…

With the recent success of the pre-training technique for NLP and image-linguistic tasks, some video-linguistic pre-training works are gradually developed to improve video-text related downstream tasks. However, most of the existing…