相关论文: Look More but Care Less in Video Recognition

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,…

Few-shot semantic segmentation aims to segment novel-class objects in a given query image with only a few labeled support images. Most advanced solutions exploit a metric learning framework that performs segmentation through matching each…

Attention Mechanism is a widely used method for improving the performance of convolutional neural networks (CNNs) on computer vision tasks. Despite its pervasiveness, we have a poor understanding of what its effectiveness stems from. It is…

It is well known that featuremap attention and multi-path representation are important for visual recognition. In this paper, we present a modularized architecture, which applies the channel-wise attention on different network branches to…

Accurately segmenting blood vessels in retinal fundus images is crucial in the early screening, diagnosing, and evaluating some ocular diseases, yet it poses a nontrivial uncertainty for the segmentation task due to various factors such as…

We address the problem of temporal localization of repetitive activities in a video, i.e., the problem of identifying all segments of a video that contain some sort of repetitive or periodic motion. To do so, the proposed method represents…

Recent works of point clouds show that mulit-frame spatio-temporal modeling outperforms single-frame versions by utilizing cross-frame information. In this paper, we further improve spatio-temporal point cloud feature learning with a…

In this paper, we focus on semantic segmentation method for point clouds of urban scenes. Our fundamental concept revolves around the collaborative utilization of diverse scene representations to benefit from different context information…

Action recognition is a key problem in computer vision that labels videos with a set of predefined actions. Capturing both, semantic content and motion, along the video frames is key to achieve high accuracy performance on this task. Most…

Visual attention has been extensively studied for learning fine-grained features in both facial expression recognition (FER) and Action Unit (AU) detection. A broad range of previous research has explored how to use attention modules to…

Dominant approaches to action detection can only provide sub-optimal solutions to the problem, as they rely on seeking frame-level detections, to later compose them into "action tubes" in a post-processing step. With this paper we radically…

Retinal diseases can cause irreversible vision loss in both eyes if not diagnosed and treated early. Since retinal diseases are so complicated, retinal imaging is likely to show two or more abnormalities. Current deep learning techniques…

Semantic segmentation is fundamental to vision systems requiring pixel-level scene understanding, yet deploying it on resource-constrained devices demands efficient architectures. Although existing methods achieve real-time inference…

Recent years have witnessed promising results of face detection using deep learning. Despite making remarkable progresses, face detection in the wild remains an open research challenge especially when detecting faces at vastly different…

We tackle a novel few-shot learning challenge, which we call few-shot semantic edge detection, aiming to localize crisp boundaries of novel categories using only a few labeled samples. We also present a Class-Agnostic Few-shot Edge…

We consider two less-emphasized temporal properties of video: 1. Temporal cues are fine-grained; 2. Temporal modeling needs reasoning. To tackle both problems at once, we exploit approximated bilinear modules (ABMs) for temporal modeling.…

Recently, flow-based frame interpolation methods have achieved great success by first modeling optical flow between target and input frames, and then building synthesis network for target frame generation. However, above cascaded…

Online action detection is a task with the aim of identifying ongoing actions from streaming videos without any side information or access to future frames. Recent methods proposed to aggregate fixed temporal ranges of invisible but…

With the widespread use of installed cameras, video-based monitoring approaches have seized considerable attention for different purposes like assisted living. Temporal redundancy and the sheer size of raw videos are the two most common…

We introduce Amortized Neural Networks (AmNets), a compute cost- and latency-aware network architecture particularly well-suited for sequence modeling tasks. We apply AmNets to the Recurrent Neural Network Transducer (RNN-T) to reduce…