Related papers: SimVTP: Simple Video Text Pre-training with Masked…

Masked Autoencoders (MAEs) learn generalizable representations for image, text, audio, video, etc., by reconstructing masked input data from tokens of the visible data. Current MAE approaches for videos rely on random patch, tube, or…

Weakly-supervised medical image segmentation is a challenging task that aims to reduce the annotation cost while keep the segmentation performance. In this paper, we present a novel framework, SimTxtSeg, that leverages simple text cues to…

Masked image modeling (MIM) has become a leading self-supervised learning strategy. MIMs such as Masked Autoencoder (MAE) learn strong representations by randomly masking input tokens for the encoder to process, with the decoder…

Pre-training on large-scale video data has become a common recipe for learning transferable spatiotemporal representations in recent years. Despite some progress, existing methods are mostly limited to highly curated datasets (e.g., K400)…

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…

Despite its success in image synthesis, we observe that diffusion probabilistic models (DPMs) often lack contextual reasoning ability to learn the relations among object parts in an image, leading to a slow learning process. To solve this…

This paper studies a conceptually simple extension of Masked Autoencoders (MAE) to spatiotemporal representation learning from videos. We randomly mask out spacetime patches in videos and learn an autoencoder to reconstruct them in pixels.…

The rapid success of Vision Large Language Models (VLLMs) often depends on the high-resolution images with abundant visual tokens, which hinders training and deployment efficiency. Current training-free visual token compression methods…

Video-language pre-trained models have shown remarkable success in guiding video question-answering (VideoQA) tasks. However, due to the length of video sequences, training large-scale video-based models incurs considerably higher costs…

In this paper, we investigate self-supervised pre-training methods for document text recognition. Nowadays, large unlabeled datasets can be collected for many research tasks, including text recognition, but it is costly to annotate them.…

The recent advance in vision-language models is largely attributed to the abundance of image-text data. We aim to replicate this success for video-language models, but there simply is not enough human-curated video-text data available. We…

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…

Pre-training visual and textual representations from large-scale image-text pairs is becoming a standard approach for many downstream vision-language tasks. The transformer-based models learn inter and intra-modal attention through a list…

In federated learning, textual prompt tuning adapts Vision-Language Models (e.g., CLIP) by tuning lightweight input tokens (or prompts) on local client data, while keeping network weights frozen. After training, only the prompts are shared…

The gap between speech and text modalities is a major challenge in speech-to-text translation (ST). Different methods have been proposed to reduce this gap, but most of them require architectural changes in ST training. In this work, we…

The quality of the latent space in visual tokenizers (e.g., VAEs) is crucial for modern generative models. However, the standard reconstruction-based training paradigm produces a latent space that is biased towards low-level information,…

This paper studies zero-shot cross-lingual transfer of vision-language models. Specifically, we focus on multilingual text-to-video search and propose a Transformer-based model that learns contextualized multilingual multimodal embeddings.…

Semantic representation is of great benefit to the video text tracking(VTT) task that requires simultaneously classifying, detecting, and tracking texts in the video. Most existing approaches tackle this task by appearance similarity in…

Masked language modeling (MLM) is one of the key sub-tasks in vision-language pretraining. In the cross-modal setting, tokens in the sentence are masked at random, and the model predicts the masked tokens given the image and the text. In…

In this paper, we present our methods and results for the Video-To-Text (VTT) task at TRECVid 2024, exploring the capabilities of Vision-Language Models (VLMs) like LLaVA and LLaVA-NeXT-Video in generating natural language descriptions for…