English
Related papers

Related papers: MoCrop: Training Free Motion Guided Cropping for E…

200 papers

Multi-object tracking (MOT) at low frame rates can reduce computational, storage and power overhead to better meet the constraints of edge devices. Many existing MOT methods suffer from significant performance degradation in low-frame-rate…

Computer Vision and Pattern Recognition · Computer Science 2023-09-13 Yiheng Liu , Junta Wu , Yi Fu

High frame-rate (HFR) videos of action recognition improve fine-grained expression while reducing the spatio-temporal relation and motion information density. Thus, large amounts of video samples are continuously required for traditional…

Computer Vision and Pattern Recognition · Computer Science 2026-03-25 Wenbo Huang , Jinghui Zhang , Xuwei Qian , Zhen Wu , Meng Wang , Lei Zhang

This paper describes AutoFocus, an efficient multi-scale inference algorithm for deep-learning based object detectors. Instead of processing an entire image pyramid, AutoFocus adopts a coarse to fine approach and only processes regions…

Computer Vision and Pattern Recognition · Computer Science 2019-08-02 Mahyar Najibi , Bharat Singh , Larry S. Davis

Recent vision-language models excel at large-scale image-text alignment but often neglect the compositional structure of language, leading to failures on tasks that hinge on word order and predicate-argument structure. We introduce…

Computation and Language · Computer Science 2025-09-26 Kin Ian Lo , Hala Hawashin , Mina Abbaszadeh , Tilen Limback-Stokin , Hadi Wazni , Mehrnoosh Sadrzadeh

We introduce MoMa, a novel modality-aware mixture-of-experts (MoE) architecture designed for pre-training mixed-modal, early-fusion language models. MoMa processes images and text in arbitrary sequences by dividing expert modules into…

Artificial Intelligence · Computer Science 2024-08-13 Xi Victoria Lin , Akshat Shrivastava , Liang Luo , Srinivasan Iyer , Mike Lewis , Gargi Ghosh , Luke Zettlemoyer , Armen Aghajanyan

Pre-trained vision-language (V-L) models such as CLIP have shown excellent generalization ability to downstream tasks. However, they are sensitive to the choice of input text prompts and require careful selection of prompt templates to…

Computer Vision and Pattern Recognition · Computer Science 2023-04-04 Muhammad Uzair Khattak , Hanoona Rasheed , Muhammad Maaz , Salman Khan , Fahad Shahbaz Khan

We present MOFA-Video, an advanced controllable image animation method that generates video from the given image using various additional controllable signals (such as human landmarks reference, manual trajectories, and another even…

Computer Vision and Pattern Recognition · Computer Science 2024-07-12 Muyao Niu , Xiaodong Cun , Xintao Wang , Yong Zhang , Ying Shan , Yinqiang Zheng

Object detection, one of the three main tasks of computer vision, has been used in various applications. The main process is to use deep neural networks to extract the features of an image and then use the features to identify the class and…

Computer Vision and Pattern Recognition · Computer Science 2022-12-14 Wenshuo Li

So far, efficient fine-tuning has become a popular strategy for enhancing the capabilities of foundation models on downstream tasks by learning plug-and-play modules. However, existing methods overlook a crucial issue: if the underlying…

Computer Vision and Pattern Recognition · Computer Science 2024-12-31 Zhengbo Wang , Jian Liang , Lijun Sheng , Ran He , Zilei Wang , Tieniu Tan

Adaptive robotics plays an essential role in achieving truly co-creative cyber physical systems. In robotic manipulation tasks, one of the biggest challenges is to estimate the pose of given workpieces. Even though the recent…

Robotics · Computer Science 2024-07-29 Dániel Horváth , Kristóf Bocsi , Gábor Erdős , Zoltán Istenes

Eliminating image blur produced by various kinds of motion has been a challenging problem. Dominant approaches rely heavily on model capacity to remove blurring by reconstructing residual from blurry observation in feature space. These…

Image and Video Processing · Electrical Eng. & Systems 2024-04-23 Chengxu Liu , Xuan Wang , Xiangyu Xu , Ruhao Tian , Shuai Li , Xueming Qian , Ming-Hsuan Yang

Optical motion capture is a foundational technology driving advancements in cutting-edge fields such as virtual reality and film production. However, system performance suffers severely under large-scale marker occlusions common in…

Computer Vision and Pattern Recognition · Computer Science 2025-08-19 Chen Qian , Danyang Li , Xinran Yu , Zheng Yang , Qiang Ma

Large pre-trained vision-language models, such as CLIP, have demonstrated state-of-the-art performance across a wide range of image classification tasks, without requiring retraining. Few-shot CLIP is competitive with existing specialized…

Computer Vision and Pattern Recognition · Computer Science 2024-09-06 Dominykas Seputis , Serghei Mihailov , Soham Chatterjee , Zehao Xiao

Field-captured video facilitates detailed studies of spatio-temporal aspects of animal locomotion, decision-making and environmental interactions including predator-prey relationships and habitat utilisation. But even though data capture is…

Computer Vision and Pattern Recognition · Computer Science 2024-10-03 Malika Nisal Ratnayake , Lex Gallon , Adel N. Toosi , Alan Dorin

Untrimmed videos on social media or those captured by robots and surveillance cameras are of varied aspect ratios. However, 3D CNNs usually require as input a square-shaped video, whose spatial dimension is smaller than the original.…

Computer Vision and Pattern Recognition · Computer Science 2021-11-23 Prithwish Jana , Swarnabja Bhaumik , Partha Pratim Mohanta

Adaptive sampling that exploits the spatiotemporal redundancy in videos is critical for always-on action recognition on wearable devices with limited computing and battery resources. The commonly used fixed sampling strategy is not…

Computer Vision and Pattern Recognition · Computer Science 2022-07-18 Khoi-Nguyen C. Mac , Minh N. Do , Minh P. Vo

The existing action tubelet detectors often depend on heuristic anchor design and placement, which might be computationally expensive and sub-optimal for precise localization. In this paper, we present a conceptually simple, computationally…

Computer Vision and Pattern Recognition · Computer Science 2020-08-25 Yixuan Li , Zixu Wang , Limin Wang , Gangshan Wu

Recent advancements in multimodal foundation models (e.g., CLIP) have excelled in zero-shot generalization. Prompt tuning involved in the knowledge transfer from foundation models to downstream tasks has gained significant attention…

Computer Vision and Pattern Recognition · Computer Science 2023-12-07 Xuejing Liu , Wei Tang , Jinghui Lu , Rui Zhao , Zhaojun Guo , Fei Tan

This paper aims at addressing the problem of substantial performance degradation at extremely low computational cost (e.g. 5M FLOPs on ImageNet classification). We found that two factors, sparse connectivity and dynamic activation function,…

Computer Vision and Pattern Recognition · Computer Science 2021-08-21 Yunsheng Li , Yinpeng Chen , Xiyang Dai , Dongdong Chen , Mengchen Liu , Lu Yuan , Zicheng Liu , Lei Zhang , Nuno Vasconcelos

Multi-object tracking (MOT) is critical in numerous real-world applications, including surveillance, autonomous driving, and robotics. Accurately predicting object motion is fundamental to MOT, but current methods struggle with the…

Computer Vision and Pattern Recognition · Computer Science 2026-05-04 Nhat-Tan Do , Le-Huy Tu , Nhi Ngoc-Yen Nguyen , Dieu-Phuong Nguyen , Trong-Hop Do
‹ Prev 1 3 4 5 6 7 10 Next ›