中文
相关论文

相关论文: 3rd Place Solution to Meta AI Video Similarity Cha…

200 篇论文

Current video retrieval efforts all found their evaluation on an instance-based assumption, that only a single caption is relevant to a query video and vice versa. We demonstrate that this assumption results in performance comparisons often…

计算机视觉与模式识别 · 计算机科学 2021-03-19 Michael Wray , Hazel Doughty , Dima Damen

Distracted driving causes thousands of deaths per year, and how to apply deep-learning methods to prevent these tragedies has become a crucial problem. In Track3 of the 6th AI City Challenge, researchers provide a high-quality video dataset…

计算机视觉与模式识别 · 计算机科学 2022-07-06 Jingjie Shang , Kunchang Li , Kaibin Tian , Haisheng Su , Yangguang Li

Video instance segmentation is a challenging task that serves as the cornerstone of numerous downstream applications, including video editing and autonomous driving. In this report, we present further improvements to the SOTA VIS method,…

计算机视觉与模式识别 · 计算机科学 2023-08-29 Tao Zhang , Xingye Tian , Yikang Zhou , Yu Wu , Shunping Ji , Cilin Yan , Xuebo Wang , Xin Tao , Yuan Zhang , Pengfei Wan

Large-scale Video Object Segmentation (LSVOS) addresses the challenge of accurately tracking and segmenting objects in long video sequences, where difficulties stem from object reappearance, small-scale targets, heavy occlusions, and…

计算机视觉与模式识别 · 计算机科学 2025-09-23 Yujie Xie , Hongyang Zhang , Zhihui Liu , Shihai Ruan

In this paper, we describe our winning approach to solving the Lane Following Challenge at the AI Driving Olympics Competition through imitation learning on a mixed set of simulation and real-world data. AI Driving Olympics is a two-stage…

机器学习 · 计算机科学 2020-07-08 Mikita Sazanovich , Konstantin Chaika , Kirill Krinkin , Aleksei Shpilman

This report presents solutions to three machine learning challenges developed as part of the Rayan AI Contest: compositional image retrieval, zero-shot anomaly detection, and backdoored model detection. In compositional image retrieval, we…

机器学习 · 计算机科学 2025-12-24 Ali Nafisi , Sina Asghari , Mohammad Saeed Arvenaghi , Hossein Shakibania

Video stabilization is a longstanding computer vision problem, particularly pixel-level synthesis solutions for video stabilization which synthesize full frames add to the complexity of this task. These techniques aim to stabilize videos by…

计算机视觉与模式识别 · 计算机科学 2024-04-10 Muhammad Kashif Ali , Eun Woo Im , Dongjin Kim , Tae Hyun Kim

In this paper, a unified three-layer hierarchical approach for solving tracking problems in multiple non-overlapping cameras is proposed. Given a video and a set of detections (obtained by any person detector), we first solve within-camera…

计算机视觉与模式识别 · 计算机科学 2017-06-21 Yonatan Tariku Tesfaye , Eyasu Zemene , Andrea Prati , Marcello Pelillo , Mubarak Shah

In recent years, online Video Instance Segmentation (VIS) methods have shown remarkable advancement with their powerful query-based detectors. Utilizing the output queries of the detector at the frame-level, these methods achieve high…

计算机视觉与模式识别 · 计算机科学 2024-03-11 Hanjung Kim , Jaehyun Kang , Miran Heo , Sukjun Hwang , Seoung Wug Oh , Seon Joo Kim

This study addresses the challenge of performing visual localization in demanding conditions such as night-time scenarios, adverse weather, and seasonal changes. While many prior studies have focused on improving image-matching performance…

计算机视觉与模式识别 · 计算机科学 2024-03-21 Khang Truong Giang , Soohwan Song , Sungho Jo

In the last decade many different algorithms have been proposed to track a generic object in videos. Their execution on recent large-scale video datasets can produce a great amount of various tracking behaviours. New trends in Reinforcement…

计算机视觉与模式识别 · 计算机科学 2020-03-10 Matteo Dunnhofer , Niki Martinel , Gian Luca Foresti , Christian Micheloni

Video captioning is an advanced multi-modal task which aims to describe a video clip using a natural language sentence. The encoder-decoder framework is the most popular paradigm for this task in recent years. However, there exist some…

计算机视觉与模式识别 · 计算机科学 2021-02-15 Haoran Chen , Jianmin Li , Xiaolin Hu

In this technical report, we present our findings from the research conducted on the Vast Vocabulary Visual Detection (V3Det) dataset for Supervised Vast Vocabulary Visual Detection task. How to deal with complex categories and detection…

计算机视觉与模式识别 · 计算机科学 2024-06-24 Peixi Wu , Bosong Chai , Xuan Nie , Longquan Yan , Zeyu Wang , Qifan Zhou , Boning Wang , Yansong Peng , Hebei Li

Multi-camera vehicle tracking is one of the most complicated tasks in Computer Vision as it involves distinct tasks including Vehicle Detection, Tracking, and Re-identification. Despite the challenges, multi-camera vehicle tracking has…

计算机视觉与模式识别 · 计算机科学 2022-04-18 Pirazh Khorramshahi , Vineet Shenoy , Michael Pack , Rama Chellappa

We extend the classical tracking-by-detection paradigm to this tracking-any-object task. Solid detection results are first extracted from TAO dataset. Some state-of-the-art techniques like \textbf{BA}lanced-\textbf{G}roup \textbf{S}oftmax…

计算机视觉与模式识别 · 计算机科学 2021-02-02 Fei Du , Bo Xu , Jiasheng Tang , Yuqi Zhang , Fan Wang , Hao Li

Image copy detection is an important task for content moderation. We introduce SSCD, a model that builds on a recent self-supervised contrastive training objective. We adapt this method to the copy detection task by changing the…

计算机视觉与模式识别 · 计算机科学 2022-03-29 Ed Pizzi , Sreya Dutta Roy , Sugosh Nagavara Ravindra , Priya Goyal , Matthijs Douze

In this paper, we introduce VCSL (Video Copy Segment Localization), a new comprehensive segment-level annotated video copy dataset. Compared with existing copy detection datasets restricted by either video-level annotation or small-scale,…

计算机视觉与模式识别 · 计算机科学 2022-06-17 Sifeng He , Xudong Yang , Chen Jiang , Gang Liang , Wei Zhang , Tan Pan , Qing Wang , Furong Xu , Chunguang Li , Jingxiong Liu , Hui Xu , Kaiming Huang , Yuan Cheng , Feng Qian , Xiaobo Zhang , Lei Yang

This paper presents a novel semi-supervised deep learning algorithm for retrieving similar 2D and 3D videos based on visual content. The proposed approach combines the power of deep convolutional and recurrent neural networks with dynamic…

计算机视觉与模式识别 · 计算机科学 2023-09-06 Yintai Ma , Diego Klabjan

Video captioning is a challenging task since it requires generating sentences describing various diverse and complex videos. Existing video captioning models lack adequate visual representation due to the neglect of the existence of gaps…

计算机视觉与模式识别 · 计算机科学 2021-10-14 Mingkang Tang , Zhanyu Wang , Zhenhua Liu , Fengyun Rao , Dian Li , Xiu Li

We present a supervised learning algorithm for text categorization which has brought the team of authors the 2nd place in the text categorization division of the 2012 Cybersecurity Data Mining Competition (CDMC'2012) and a 3rd prize…

信息检索 · 计算机科学 2013-07-11 Hubert Haoyang Duan , Vladimir Pestov , Varun Singla