English
Related papers

Related papers: Evolution-Preserving Dense Trajectory Descriptors

200 papers

High-quality 3D reconstructions from endoscopy video play an important role in many clinical applications, including surgical navigation where they enable direct video-CT registration. While many methods exist for general multi-view 3D…

Computer Vision and Pattern Recognition · Computer Science 2020-03-30 Xingtong Liu , Yiping Zheng , Benjamin Killeen , Masaru Ishii , Gregory D. Hager , Russell H. Taylor , Mathias Unberath

In this work, we present novel temporal encoding methods for action and activity classification by extending the unsupervised rank pooling temporal encoding method in two ways. First, we present "discriminative rank pooling" in which the…

Computer Vision and Pattern Recognition · Computer Science 2017-05-31 Basura Fernando , Stephen Gould

Deep ConvNets have shown its good performance in image classification tasks. However it still remains as a problem in deep video representation for action recognition. The problem comes from two aspects: on one hand, current video ConvNets…

Computer Vision and Pattern Recognition · Computer Science 2015-11-09 Shichao Zhao , Yanbin Liu , Yahong Han , Richang Hong

Landmark-based human action recognition in videos is a challenging task in computer vision. One key step is to design a generic approach that generates discriminative features for the spatial structure and temporal dynamics. To this end, we…

Computer Vision and Pattern Recognition · Computer Science 2019-12-13 Weixin Yang , Terry Lyons , Hao Ni , Cordelia Schmid , Lianwen Jin

Numerous methods for human activity recognition have been proposed in the past two decades. Many of these methods are based on sparse representation, which describes the whole video content by a set of local features. Trajectories, being…

Computer Vision and Pattern Recognition · Computer Science 2019-05-15 Pejman Habashi , Boubakeur Boufama , Imran Shafiq Ahmad

In this paper, we propose a discriminative video representation for event detection over a large scale video dataset when only limited hardware resources are available. The focus of this paper is to effectively leverage deep Convolutional…

Computer Vision and Pattern Recognition · Computer Science 2014-11-17 Zhongwen Xu , Yi Yang , Alexander G. Hauptmann

While Reinforcement Learning with Verifiable Rewards (RLVR) has proven effective for closed-ended tasks, extending it to open-ended social language games via self-play reveals a critical issue: evolution impasse. Due to the vast strategy…

Computation and Language · Computer Science 2026-05-12 Minzheng Wang , Run Luo , Yanbo Wang , Zichen Liu , Yuqiao Tan , Tao Tan , Xu Nan , Yinhe Zheng , Wenji Mao

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…

Computer Vision and Pattern Recognition · Computer Science 2020-03-10 Matteo Dunnhofer , Niki Martinel , Gian Luca Foresti , Christian Micheloni

The introduction of low-cost RGB-D sensors has promoted the research in skeleton-based human action recognition. Devising a representation suitable for characterising actions on the basis of noisy skeleton sequences remains a challenge,…

Computer Vision and Pattern Recognition · Computer Science 2015-04-21 Ruizhi Qiao , Lingqiao Liu , Chunhua Shen , Anton von den Hengel

In this paper, we present a new feature representation for first-person videos. In first-person video understanding (e.g., activity recognition), it is very important to capture both entire scene dynamics (i.e., egomotion) and salient local…

Computer Vision and Pattern Recognition · Computer Science 2015-05-07 M. S. Ryoo , Brandon Rothrock , Larry Matthies

The rapid advancement of diffusion-based image generators has made it increasingly difficult to distinguish generated from real images. This erodes trust in digital media, making it critical to develop generated image detectors that remain…

Computer Vision and Pattern Recognition · Computer Science 2025-10-01 Ana Vasilcoiu , Ivona Najdenkoska , Zeno Geradts , Marcel Worring

Sequential prediction is challenging in regimes of delayed disambiguation, where early observations are ambiguous and multiple latent explanations remain plausible until sufficient evidence accumulates. Standard approaches based on marginal…

Machine Learning · Computer Science 2026-05-20 Omer Haq

Accurately predicting how agents move in dynamic scenes is essential for safe autonomous driving. State-of-the-art motion forecasting models rely on datasets with manually annotated or post-processed trajectories. However, building these…

Computer Vision and Pattern Recognition · Computer Science 2026-02-27 Yihong Xu , Yuan Yin , Éloi Zablocki , Tuan-Hung Vu , Alexandre Boulch , Matthieu Cord

Popular deep models for action recognition in videos generate independent predictions for short clips, which are then pooled heuristically to assign an action label to the full video segment. As not all frames may characterize the…

Computer Vision and Pattern Recognition · Computer Science 2018-04-02 Jue Wang , Anoop Cherian , Fatih Porikli , Stephen Gould

Deep neural networks, despite their remarkable success, remain fundamentally limited in their ability to perform Continual Learning (CL). While most current methods aim to enhance the capabilities of a single model, Inspired by the…

Machine Learning · Computer Science 2025-08-01 Aojun Lu , Junchao Ke , Chunhui Ding , Jiahao Fan , Jiancheng Lv , Yanan Sun

Video diffusion models provide powerful real-world simulators for embodied AI but remain limited in controllability for robotic manipulation. Recent works on trajectory-conditioned video generation address this gap but often rely on 2D…

Computer Vision and Pattern Recognition · Computer Science 2025-12-17 Yang Bai , Liudi Yang , George Eskandar , Fengyi Shen , Mohammad Altillawi , Ziyuan Liu , Gitta Kutyniok

Trajectory prediction is a challenging problem that requires considering interactions among multiple actors and the surrounding environment. While data-driven approaches have been used to address this complex problem, they suffer from…

Computer Vision and Pattern Recognition · Computer Science 2024-03-18 Daehee Park , Jaeseok Jeong , Sung-Hoon Yoon , Jaewoo Jeong , Kuk-Jin Yoon

Most state-of-the-art methods for action recognition rely only on 2D spatial features encoding appearance, motion or pose. However, 2D data lacks the depth information, which is crucial for recognizing fine-grained actions. In this paper,…

Computer Vision and Pattern Recognition · Computer Science 2020-11-30 Mattia Segu , Federico Pirovano , Gianmario Fumagalli , Amedeo Fabris

We propose an unsupervised approach for discovering characteristic motion patterns in videos of highly articulated objects performing natural, unscripted behaviors, such as tigers in the wild. We discover consistent patterns in a bottom-up…

Computer Vision and Pattern Recognition · Computer Science 2015-04-27 Luca Del Pero , Susanna Ricco , Rahul Sukthankar , Vittorio Ferrari

Despite the numerous applications and success of deep reinforcement learning in many control tasks, it still suffers from many crucial problems and limitations, including temporal credit assignment with sparse reward, absence of effective…

Neural and Evolutionary Computing · Computer Science 2022-09-20 Marzieh Sadat Esmaeeli , Hamed Malek