paper-with-me

Papers

OmniVL:One Foundation Model for Image-Language and Video-Language Tasks

2022-09-15 · Junke Wang, Dongdong Chen, Zuxuan Wu, Chong Luo, Luowei Zhou, Yucheng Zhao, Yujia Xie, Ce Liu, Yu-Gang Jiang, Lu Yuan

This paper presents OmniVL, a new foundation model to support both image-language and video-language tasks using one universal architecture. It adopts a unified transformer-based visual encoder for both image and video inputs, and thus can perform joint image-language and video-language pretraining. We demonstrate, for the first time, such a paradigm benefits both image and video tasks, as opposed to the conventional one-directional transfer (e.g., use image-language to help video-language). To this end, we propose a decoupled joint pretraining of image-language and video-language to effectively decompose the vision-language modeling into spatial and temporal dimensions and obtain performance boost on both image and video tasks. Moreover, we introduce a novel unified vision-language contrastive (UniVLC) loss to leverage image-text, video-text, image-label (e.g., image classification), video-label (e.g., video action recognition) data together, so that both supervised and noisily supervised pretraining data are utilized as much as possible. Without incurring extra task-specific adaptors, OmniVL can simultaneously support visual only tasks (e.g., image classification, video action recognition), cross-modal alignment tasks (e.g., image/video-text retrieval), and multi-modal understanding and generation tasks (e.g., image/video question answering, captioning). We evaluate OmniVL on a wide range of downstream tasks and achieve state-of-the-art or competitive results with similar model size and data scale.

📄 PDF Abstract BibTeX arXiv:2209.07526

Code (0)

등록된 구현이 없습니다.

Tasks

Action ClassificationAction Recognitioncross-modal alignmentCross-Modal RetrievalImage Captioningimage-classificationImage ClassificationLanguage ModelingLanguage ModellingQuestion AnsweringRetrievalTemporal Action LocalizationText RetrievalVideo CaptioningVideo Question AnsweringVideo RetrievalVideo-Text RetrievalVisual Question Answering (VQA)Zero-Shot Video Retrieval

Similar Papers 제목 키워드 기반

OmniVLA: An Omni-Modal Vision-Language-Action Model for Robot Navigation

2025-09-23 · Noriaki Hirose, Catherine Glossop, Dhruv Shah, Sergey Levine arxiv

Humans can flexibly interpret and compose different goal specifications, such as language instructions, spatial coordinates, or visual references, when navigating to a destination. In contrast, most existing robotic navi…

Robot Navigation

OmniVL-Guard: Towards Unified Vision-Language Forgery Detection and Grounding via Balanced RL

2026-02-11 · Jinjie Shen, Jing Wu, Yaxiong Wang, Lechao Cheng 외 arxiv

Existing forgery detection methods are often limited to uni-modal or bi-modal settings, failing to handle the interleaved text, images, and videos prevalent in real-world misinformation. To bridge this gap, this paper ta…

Reinforcement Learning

OmniVL-Guard Pro: A Tool-Augmented Agent for Omnibus Vision-Language Forensics

2026-05-16 · Jinjie Shen, Zheng Huang, Yuchen Zhang, Yujiao Wu 외 arxiv

Existing vision-language forgery detection and grounding methods operate under a closed-world paradigm, assuming verification can be completed by the model alone. However, self-contained MLLMs are constrained by finite p…

Zero-shot GeneralizationReinforcement LearningFace Detection

OmniVLM: A Token-Compressed, Sub-Billion-Parameter Vision-Language Model for Efficient On-Device Inference

2024-12-16 · Wei Chen, Zhiyuan Li, Shuo Xin

We present OmniVLM, a sub-billion-parameter vision-language model for efficient on-device inference. OmniVLM introduces a token compression mechanism that reduces visual token sequence length from 729 to 81 tokens, signi…

Language ModelingLanguage Modelling

OmniVLA: Physically-Grounded Multimodal VLA with Unified Multi-Sensor Perception for Robotic Manipulation

2025-11-03 · Heyu Guo, Shanmu Wang, Ruichun Ma, Shiqi Jiang 외 arxiv

Vision-language-action (VLA) models have shown strong generalization for robotic action prediction through large-scale vision-language pretraining. However, most existing models rely solely on RGB cameras, limiting their…