paper-with-me

홈 › Papers

Beyond still images: Temporal features and input variance resilience

2023-11-01 · Amir Hosein Fadaei, Mohammad-Reza A. Dehaqani

Traditionally, vision models have predominantly relied on spatial features extracted from static images, deviating from the continuous stream of spatiotemporal features processed by the brain in natural vision. While numerous video-understanding models have emerged, incorporating videos into image-understanding models with spatiotemporal features has been limited. Drawing inspiration from natural vision, which exhibits remarkable resilience to input changes, our research focuses on the development of a brain-inspired model for vision understanding trained with videos. Our findings demonstrate that models that train on videos instead of still images and include temporal features become more resilient to various alternations on input media.

📄 PDF Abstract BibTeX arXiv:2311.00800

Code (0)

등록된 구현이 없습니다.

Tasks

Video Understanding

Methods 이 논문이 사용한 방법론

Focus 설명 없음

Similar Papers 제목 키워드 기반

Learning to Reason: Temporal Saliency Distillation for Interpretable Knowledge Transfer

2026-01-07 · Nilushika Udayangani Hewa Dehigahawattage, Kishor Nandakishor, Marimuthu Palaniswami arxiv

Knowledge distillation has proven effective for model compression by transferring knowledge from a larger network called the teacher to a smaller network called the student. Current knowledge distillation in time series …

Knowledge DistillationTime Series AnalysisModel Compression

Temporal Hallucinating for Action Recognition With Few Still Images

2018-06-01 · CVPR 2018 6 · Yali Wang, Lei Zhou, Yu Qiao

Action recognition in still images has been recently promoted by deep learning. However, the success of these deep models heavily depends on huge amount of training images for various action categories, which may not be …

Action RecognitionAction Recognition In Still ImagesDomain AdaptationTemporal Action Localization

TASeg: Temporal Aggregation Network for LiDAR Semantic Segmentation

2024-07-13 · CVPR 2024 1 · Xiaopei Wu, Yuenan Hou, Xiaoshui Huang, Binbin Lin 외

Training deep models for LiDAR semantic segmentation is challenging due to the inherent sparsity of point clouds. Utilizing temporal data is a natural remedy against the sparsity problem as it makes the input signal dens…

LIDAR Semantic SegmentationSemantic Segmentation

Video Saliency Detection by 3D Convolutional Neural Networks

2018-07-12 · Guanqun Ding, Yuming Fang

Different from salient object detection methods for still images, a key challenging for video saliency detection is how to extract and combine spatial and temporal features. In this paper, we present a novel and effectiv…

Objectobject-detectionObject DetectionRGB Salient Object Detection+5

SwiftVLA: Unlocking Spatiotemporal Dynamics for Lightweight VLA Models at Minimal Overhead

2025-11-30 · Chaojun Ni, Cheng Chen, Xiaofeng Wang, Zheng Zhu 외 arxiv

Vision-Language-Action (VLA) models built on pretrained Vision-Language Models (VLMs) show strong potential but are limited in practicality due to their large parameter counts. To mitigate this issue, using a lightweight…