paper-with-me

Papers

MeMOT: Multi-Object Tracking with Memory

2022-03-31 · CVPR 2022 1 · Jiarui Cai, Mingze Xu, Wei Li, Yuanjun Xiong, Wei Xia, Zhuowen Tu, Stefano Soatto

We propose an online tracking algorithm that performs the object detection and data association under a common framework, capable of linking objects after a long time span. This is realized by preserving a large spatio-temporal memory to store the identity embeddings of the tracked objects, and by adaptively referencing and aggregating useful information from the memory as needed. Our model, called MeMOT, consists of three main modules that are all Transformer-based: 1) Hypothesis Generation that produce object proposals in the current video frame; 2) Memory Encoding that extracts the core information from the memory for each tracked object; and 3) Memory Decoding that solves the object detection and data association tasks simultaneously for multi-object tracking. When evaluated on widely adopted MOT benchmark datasets, MeMOT observes very competitive performance.

📄 PDF Abstract BibTeX arXiv:2203.16761

Code (0)

등록된 구현이 없습니다.

Tasks

Multi-Object TrackingObjectobject-detectionObject DetectionObject Tracking

Similar Papers 제목 키워드 기반

MeMOTR: Long-Term Memory-Augmented Transformer for Multi-Object Tracking

2023-07-28 · ICCV 2023 1 · Ruopeng Gao, LiMin Wang

As a video task, Multiple Object Tracking (MOT) is expected to capture temporal information of targets effectively. Unfortunately, most existing methods only explicitly exploit the object features between adjacent frames…

Multi-Object TrackingMultiple Object TrackingObjectObject Tracking

Clip-level Uncertainty and Temporal-aware Active Learning for End-to-End Multi-Object Tracking

2026-05-11 · Riku Inoue, Shogo Sato, Kazuhiko Murasaki, Tomoyasu Shimada 외 arxiv

Multi-Object Tracking (MOT) in dynamic environments relies on robust temporal reasoning to maintain consistent object identities over time. Transformer-based end-to-end MOT models achieve strong performance by explicitly…

Multi-Object TrackingActive Learning

MemoTime: Memory-Augmented Temporal Knowledge Graph Enhanced Large Language Model Reasoning

2025-10-15 · Xingyu Tan, Xiaoyang Wang, Qing Liu, Xiwei Xu 외 arxiv

Large Language Models (LLMs) have achieved impressive reasoning abilities, but struggle with temporal understanding, especially when questions involve multiple entities, compound operators, and evolving event sequences. …

Knowledge Graphs

LT3 at SemEval-2020 Task 8: Multi-Modal Multi-Task Learning for Memotion Analysis

2020-12-01 · SEMEVAL 2020 · Pranaydeep Singh, Nina Bauwelinck, Els Lefever

Internet memes have become a very popular mode of expression on social media networks today. Their multi-modal nature, caused by a mixture of text and image, makes them a very challenging research object for automatic an…

Continual LearningMulti-Task Learning

NUAA-QMUL-AIIT at Memotion 3: Multi-modal Fusion with Squeeze-and-Excitation for Internet Meme Emotion Analysis

2023-02-16 · XIAOYU GUO, Jing Ma, Arkaitz Zubiaga

This paper describes the participation of our NUAA-QMUL-AIIT team in the Memotion 3 shared task on meme emotion analysis. We propose a novel multi-modal fusion method, Squeeze-and-Excitation Fusion (SEFusion), and embed …

Emotion ClassificationEmotion Recognition