相关论文: Collaborative Spatio-temporal Feature Learning for…

We propose a novel scheme for human action recognition in videos, using a 3-dimensional Convolutional Neural Network (3D CNN) based classifier. Traditionally in deep learning based human activity recognition approaches, either a few random…

This paper addresses the task of segmenting class-agnostic objects in semi-supervised setting. Although previous detection based methods achieve relatively good performance, these approaches extract the best proposal by a greedy strategy,…

Video prediction aims to predict future frames by modeling the complex spatiotemporal dynamics in videos. However, most of the existing methods only model the temporal information and the spatial information for videos in an independent…

Two-stream Convolutional Networks (ConvNets) have shown strong performance for human action recognition in videos. Recently, Residual Networks (ResNets) have arisen as a new technique to train extremely deep architectures. In this paper, we…

Learning image representations with ConvNets by pre-training on ImageNet has proven useful across many visual understanding tasks including object detection, semantic segmentation, and image captioning. Although any image representation can…

Deep neural networks have achieved remarkable success for video-based action recognition. However, most of existing approaches cannot be deployed in practice due to the high computational cost. To address this challenge, we propose a new…

Most video based action recognition approaches create the video-level representation by temporally pooling the features extracted at each frame. The pooling methods that they adopt, however, usually completely or partially neglect the…

The modeling, computational cost, and accuracy of traditional Spatio-temporal networks are the three most concentrated research topics in video action recognition. The traditional 2D convolution has a low computational cost, but it cannot…

In this paper, we introduce Coarse-Fine Networks, a two-stream architecture which benefits from different abstractions of temporal resolution to learn better video representations for long-term motion. Traditional Video models process…

Popular representation learning methods encourage feature invariance under transformations applied at the input. However, in 3D perception tasks like object localization and segmentation, outputs are naturally equivariant to some…

We present a novel embedding approach for video instance segmentation. Our method learns a spatio-temporal embedding integrating cues from appearance, motion, and geometry; a 3D causal convolutional network models motion, and a monocular…

In this work we address the challenging problem of unsupervised learning from videos. Existing methods utilize the spatio-temporal continuity in contiguous video frames as regularization for the learning process. Typically, this temporal…

Action Detection is a complex task that aims to detect and classify human actions in video clips. Typically, it has been addressed by processing fine-grained features extracted from a video classification backbone. Recently, thanks to the…

While recent large-scale video-language pre-training made great progress in video question answering, the design of spatial modeling of video-language models is less fine-grained than that of image-language models; existing practices of…

Spatiotemporal action recognition is the task of locating and classifying actions in videos. Our project applies this task to analyzing video footage of restaurant workers preparing food, for which potential applications include automated…

This paper describes a network that captures multimodal correlations over arbitrary timestamps. The proposed scheme operates as a complementary, extended network over a multimodal convolutional neural network (CNN). Spatial and temporal…

Generating video descriptions automatically is a challenging task that involves a complex interplay between spatio-temporal visual features and language models. Given that videos consist of spatial (frame-level) features and their temporal…

Self-supervised video representation methods typically focus on the representation of temporal attributes in videos. However, the role of stationary versus non-stationary attributes is less explored: Stationary features, which remain…

A key challenge in video enhancement and action recognition is to fuse useful information from neighboring frames. Recent works suggest establishing accurate correspondences between neighboring frames before fusing temporal information.…

We address the problem of generating video features for action recognition. The spatial pyramid and its variants have been very popular feature models due to their success in balancing spatial location encoding and spatial invariance.…