English
Related papers

Related papers: Atom: Efficient On-Device Video-Language Pipelines…

200 papers

This work proposes an industry-level omni-modal large language model (LLM) pipeline that integrates auditory, visual, and linguistic modalities to overcome challenges such as limited tri-modal datasets, high computational costs, and complex…

Text-to-video retrieval enables users to find relevant video content using natural language queries, a task that has grown increasingly important with the rapid expansion of online video. Over the past six years, research has produced…

Video Language Models (VideoLMs) enable AI systems to understand temporal dynamics in videos. To fit within the maximum context window constraint, current methods use keyframe sampling which often misses both macro-level events and…

Computer Vision and Pattern Recognition · Computer Science 2026-03-31 Sayan Deb Sarkar , Rémi Pautrat , Ondrej Miksik , Marc Pollefeys , Iro Armeni , Mahdi Rad , Mihai Dusmanu

Vision-language models (VLMs) integrate visual and textual information, enabling a wide range of applications such as image captioning and visual question answering, making them crucial for modern AI systems. However, their high…

Computer Vision and Pattern Recognition · Computer Science 2025-07-03 Gaurav Shinde , Anuradha Ravi , Emon Dey , Shadman Sakib , Milind Rampure , Nirmalya Roy

Recently, improving the relevance and diversity of dialogue system has attracted wide attention. For a post x, the corresponding response y is usually diverse in the real-world corpus, while the conventional encoder-decoder model tends to…

Computation and Language · Computer Science 2019-05-16 Ganbin Zhou , Ping Luo , Jingwu Chen , Fen Lin , Leyu Lin , Qing He

Recently, video generation has achieved significant rapid development based on superior text-to-image generation techniques. In this work, we propose a high fidelity framework for image-to-video generation, named AtomoVideo. Based on…

Computer Vision and Pattern Recognition · Computer Science 2024-03-06 Litong Gong , Yiran Zhu , Weijie Li , Xiaoyang Kang , Biao Wang , Tiezheng Ge , Bo Zheng

Most video captioning models are designed to process short video clips of few seconds and output text describing low-level visual concepts (e.g., objects, scenes, atomic actions). However, most real-world videos last for minutes or hours…

Computer Vision and Pattern Recognition · Computer Science 2024-05-20 Md Mohaiminul Islam , Ngan Ho , Xitong Yang , Tushar Nagarajan , Lorenzo Torresani , Gedas Bertasius

Recent advancements in large language models (LLMs) have driven interest in billion-scale retrieval models with strong generalization across retrieval tasks and languages. Additionally, progress in large vision-language models has created…

Information Retrieval · Computer Science 2025-05-06 Xueguang Ma , Luyu Gao , Shengyao Zhuang , Jiaqi Samantha Zhan , Jamie Callan , Jimmy Lin

Segment Anything Model 2 (SAM 2) has emerged as a powerful tool for video object segmentation and tracking anything. Key components of SAM 2 that drive the impressive video object segmentation performance include a large multistage image…

We present Perceive Anything Model (PAM), a conceptually straightforward and efficient framework for comprehensive region-level visual understanding in images and videos. Our approach extends the powerful segmentation model SAM 2 by…

Computer Vision and Pattern Recognition · Computer Science 2025-06-06 Weifeng Lin , Xinyu Wei , Ruichuan An , Tianhe Ren , Tingwei Chen , Renrui Zhang , Ziyu Guo , Wentao Zhang , Lei Zhang , Hongsheng Li

Experts in machine learning leverage domain knowledge to navigate decisions in model selection, hyperparameter optimization, and resource allocation. This is particularly critical for fine-tuning language models (LMs), where repeated trials…

Computation and Language · Computer Science 2025-10-07 Ernesto L. Estevanell-Valladares , Suilan Estevez-Velarde , Yoan Gutiérrez , Andrés Montoyo , Ruslan Mitkov

The advancement of artificial intelligence (AI) for organ segmentation and tumor detection is propelled by the growing availability of computed tomography (CT) datasets with detailed, per-voxel annotations. However, these AI models often…

Image and Video Processing · Electrical Eng. & Systems 2024-05-29 Jie Liu , Yixiao Zhang , Kang Wang , Mehmet Can Yavuz , Xiaoxi Chen , Yixuan Yuan , Haoliang Li , Yang Yang , Alan Yuille , Yucheng Tang , Zongwei Zhou

Hyperparameter tuning of multi-stage pipelines introduces a significant computational burden. Motivated by the observation that work can be reused across pipelines if the intermediate computations are the same, we propose a pipeline-aware…

Machine Learning · Computer Science 2019-03-14 Liam Li , Evan Sparks , Kevin Jamieson , Ameet Talwalkar

Pipeline parallelism (PP) is widely used for training large language models (LLMs), yet its scalability is often constrained by high activation memory consumption as the number of in-flight microbatches grows with the degree of PP. In this…

Machine Learning · Computer Science 2025-07-01 Xinyi Wan , Penghui Qi , Guangxing Huang , Min Lin , Jialin Li

Large language models (LLMs) are commonly adapted for diverse downstream tasks via parameter-efficient fine-tuning techniques such as Low-Rank Adapters (LoRA). While adapters can be combined to handle multiple tasks separately, standard…

The proliferation of camera-enabled devices and large video repositories has led to a diverse set of video analytics applications. These applications rely on video pipelines, represented as DAGs of operations, to transform videos, process…

Distributed, Parallel, and Cluster Computing · Computer Science 2021-05-31 Francisco Romero , Mark Zhao , Neeraja J. Yadwadkar , Christos Kozyrakis

Machine learning models deployed on edge devices have enabled numerous exciting new applications, such as humanoid robots, AR glasses, and autonomous vehicles. However, the computing resources available on these edge devices are not…

Machine Learning · Computer Science 2024-11-15 Jinjie Liu , Hang Qiu

We introduce Model-Distributed Inference for Large-Language Models (MDI-LLM), a novel framework designed to facilitate the deployment of state-of-the-art large-language models (LLMs) across low-power devices at the edge. This is…

Machine Learning · Computer Science 2025-05-27 Davide Macario , Hulya Seferoglu , Erdem Koyuncu

What makes good representations for video understanding, such as anticipating future activities, or answering video-conditioned questions? While earlier approaches focus on end-to-end learning directly from video pixels, we propose to…

Computer Vision and Pattern Recognition · Computer Science 2024-07-16 Shijie Wang , Qi Zhao , Minh Quan Do , Nakul Agarwal , Kwonjoon Lee , Chen Sun

Most of the speech recognition systems recover only words in the speech and fail to capture emotions. Users have to manually add emoji(s) in text for adding tone and making communication fun. Though there is much work done on punctuation…

Computation and Language · Computer Science 2022-02-08 Sumit Kumar , Harichandana B S S , Himanshu Arora