English
Related papers

Related papers: Learning Discriminative Prototypes with Dynamic Ti…

200 papers

Recognizing instances at different scales simultaneously is a fundamental challenge in visual detection problems. While spatial multi-scale modeling has been well studied in object detection, how to effectively apply a multi-scale…

Computer Vision and Pattern Recognition · Computer Science 2019-02-19 Da Zhang , Xiyang Dai , Yuan-Fang Wang

Humans can learn concepts or recognize items from just a handful of examples, while machines require many more samples to perform the same task. In this paper, we build a computational model to investigate the possibility of this kind of…

Artificial Intelligence · Computer Science 2016-11-09 Wen-Chieh Fang , Yi-ting Chiang

Applying an image processing algorithm independently to each video frame often leads to temporal inconsistency in the resulting video. To address this issue, we present a novel and general approach for blind video temporal consistency. Our…

Computer Vision and Pattern Recognition · Computer Science 2022-01-28 Chenyang Lei , Yazhou Xing , Hao Ouyang , Qifeng Chen

Recently, video classification attracts intensive research efforts. However, most existing works are based on framelevel visual features, which might fail to model the temporal information, e.g. characteristics accumulated along time. In…

Computer Vision and Pattern Recognition · Computer Science 2016-08-18 Haimin Zhang

We propose a Dynamic Scale Training paradigm (abbreviated as DST) to mitigate scale variation challenge in object detection. Previous strategies like image pyramid, multi-scale training, and their variants are aiming at preparing…

Computer Vision and Pattern Recognition · Computer Science 2021-03-16 Yukang Chen , Peizhen Zhang , Zeming Li , Yanwei Li , Xiangyu Zhang , Lu Qi , Jian Sun , Jiaya Jia

Traditional discriminative computer vision relies predominantly on static projections, mapping input features to outputs in a single computational step. Although efficient, this paradigm lacks the iterative refinement and robustness…

Computer Vision and Pattern Recognition · Computer Science 2026-03-17 Om Govind Jha , Manoj Bamniya , Ayon Borthakur

Visual features are of vital importance for human action understanding in videos. This paper presents a new video representation, called trajectory-pooled deep-convolutional descriptor (TDD), which shares the merits of both hand-crafted…

Computer Vision and Pattern Recognition · Computer Science 2016-11-17 Limin Wang , Yu Qiao , Xiaoou Tang

This work investigates the problem of learning temporal interaction networks. A temporal interaction network consists of a series of chronological interactions between users and items. Previous methods tackle this problem by using different…

Social and Information Networks · Computer Science 2021-07-09 Jiangxia Cao , Xixun Lin , Xin Cong , Shu Guo , Hengzhu Tang , Tingwen Liu , Bin Wang

World models are essential for autonomous robotic planning. However, the substantial computational overhead of existing dense Transformerbased models significantly hinders real-time deployment. To address this efficiency-performance…

Computer Vision and Pattern Recognition · Computer Science 2026-03-06 Shicheng Yin , Kaixuan Yin , Weixing Chen , Yang Liu , Guanbin Li , Liang Lin

Class-incremental learning (CIL) aims to learn new classes while retaining previous knowledge. Although pre-trained model (PTM) based approaches show strong performance, directly fine-tuning PTMs on incremental task streams often causes…

Machine Learning · Computer Science 2025-12-02 Zhiming Xu , Suorong Yang , Baile Xu , Furao Shen , Jian Zhao

Most recent studies on detecting and localizing temporal anomalies have mainly employed deep neural networks to learn the normal patterns of temporal data in an unsupervised manner. Unlike them, the goal of our work is to fully utilize…

Computer Vision and Pattern Recognition · Computer Science 2021-08-17 Dongha Lee , Sehun Yu , Hyunjun Ju , Hwanjo Yu

Unsupervised representation learning for dynamic graphs has attracted a lot of research attention in recent years. Compared with static graph, the dynamic graph is a comprehensive embodiment of both the intrinsic stable characteristics of…

Social and Information Networks · Computer Science 2023-08-17 Kaike Zhang , Qi Cao , Gaolin Fang , Bingbing Xu , Hongjian Zou , Huawei Shen , Xueqi Cheng

Typical neural networks with external memory do not effectively separate capacity for episodic and working memory as is required for reasoning in humans. Applying knowledge gained from psychological studies, we designed a new model called…

Machine Learning · Computer Science 2018-10-01 T. S. Jayram , Younes Bouhadjar , Ryan L. McAvoy , Tomasz Kornuta , Alexis Asseman , Kamil Rocki , Ahmet S. Ozcan

In this paper, we develop the continuous time dynamic topic model (cDTM). The cDTM is a dynamic topic model that uses Brownian motion to model the latent topics through a sequential collection of documents, where a "topic" is a pattern of…

Information Retrieval · Computer Science 2015-05-19 Chong Wang , David Blei , David Heckerman

In this paper, we propose to improve the traditional use of RNNs by employing a many to many model for video classification. We analyze the importance of modeling spatial layout and temporal encoding for daily living action recognition.…

Computer Vision and Pattern Recognition · Computer Science 2018-06-18 Srijan Das , Michal Koperski , Francois Bremond , Gianpiero Francesca

This paper tackles the problem of novel category discovery (NCD), which aims to discriminate unknown categories in large-scale image collections. The NCD task is challenging due to the closeness to the real-world scenarios, where we have…

Computer Vision and Pattern Recognition · Computer Science 2022-08-02 Lu Zhang , Lu Qi , Xu Yang , Hong Qiao , Ming-Hsuan Yang , Zhiyong Liu

Frame reconstruction (current or future frame) based on Auto-Encoder (AE) is a popular method for video anomaly detection. With models trained on the normal data, the reconstruction errors of anomalous scenes are usually much larger than…

Computer Vision and Pattern Recognition · Computer Science 2021-05-11 Hui Lv , Chen Chen , Zhen Cui , Chunyan Xu , Yong Li , Jian Yang

Temporal action segmentation approaches have been very successful recently. However, annotating videos with frame-wise labels to train such models is very expensive and time consuming. While weakly supervised methods trained using only…

Computer Vision and Pattern Recognition · Computer Science 2021-03-29 Zhe Li , Yazan Abu Farha , Juergen Gall

Nighttime UAV tracking under low-illuminated scenarios has achieved great progress by domain adaptation (DA). However, previous DA training-based works are deficient in narrowing the discrepancy of temporal contexts for UAV trackers. To…

Computer Vision and Pattern Recognition · Computer Science 2024-09-30 Changhong Fu , Yiheng Wang , Liangliang Yao , Guangze Zheng , Haobo Zuo , Jia Pan

We present a temporal 6-DOF tracking method which leverages deep learning to achieve state-of-the-art performance on challenging datasets of real world capture. Our method is both more accurate and more robust to occlusions than the…

Computer Vision and Pattern Recognition · Computer Science 2017-08-17 Mathieu Garon , Jean-François Lalonde