Related papers: Optimizing Video Object Detection via a Scale-Time…
We propose a novel solution for semi-supervised video object segmentation. By the nature of the problem, available cues (e.g. video frame(s) with object masks) become richer with the intermediate predictions. However, the existing methods…
In the current salient object detection network, the most popular method is using U-shape structure. However, the massive number of parameters leads to more consumption of computing and storage resources which are not feasible to deploy on…
The goal of this paper is to discover, segment, and track independently moving objects in complex visual scenes. Previous approaches have explored the use of optical flow for motion segmentation, leading to imperfect predictions due to…
We propose AffordanceNet, a new deep learning approach to simultaneously detect multiple objects and their affordances from RGB images. Our AffordanceNet has two branches: an object detection branch to localize and classify the object, and…
Real-time detection of objects in the 3D scene is one of the tasks an autonomous agent needs to perform for understanding its surroundings. While recent Deep Learning-based solutions achieve satisfactory performance, their high…
Driven by advances in computer vision and the falling costs of camera hardware, organizations are deploying video cameras en masse for the spatial monitoring of their physical premises. Scaling video analytics to massive camera deployments,…
The problem of video object segmentation can become extremely challenging when multiple instances co-exist. While each instance may exhibit large scale and pose variations, the problem is compounded when instances occlude each other causing…
In recent years, deep learning based visual tracking methods have obtained great success owing to the powerful feature representation ability of Convolutional Neural Networks (CNNs). Among these methods, classification-based tracking…
Recently, SpineNet has demonstrated promising results on object detection and image classification over ResNet model. However, it is unclear if the improvement adds up when combining scale-permuted backbone with advanced efficient…
Real-time efficient perception is critical for autonomous navigation and city scale sensing. Orthogonal to architectural improvements, streaming perception approaches have exploited adaptive sampling improving real-time detection…
We propose a Dynamic Scale Training paradigm (abbreviated as DST) to mitigate scale variation challenge in object detection. Previous strategies like image pyramid, multi-scale training, and their variants are aiming at preparing…
Recently, Neural architecture search has achieved great success on classification tasks for mobile devices. The backbone network for object detection is usually obtained on the image classification task. However, the architecture which is…
Motivated by emerging vision-based intelligent services, we consider the problem of rate adaptation for high quality and low delay visual information delivery over wireless networks using scalable video coding. Rate adaptation in this…
Accurately localising object proposals is an important precondition for high detection rate for the state-of-the-art object detection frameworks. The accuracy of an object detection method has been shown highly related to the average recall…
Dense features are important for detecting minute objects in images. Unfortunately, despite the remarkable efficacy of the CNN models in multi-scale object detection, CNN models often fail to detect smaller objects in images due to the loss…
We present SlowFast networks for video recognition. Our model involves (i) a Slow pathway, operating at low frame rate, to capture spatial semantics, and (ii) a Fast pathway, operating at high frame rate, to capture motion at fine temporal…
Spatial-wise dynamic convolution has become a promising approach to improving the inference efficiency of deep networks. By allocating more computation to the most informative pixels, such an adaptive inference paradigm reduces the spatial…
In this paper, we propose a general and efficient pre-training paradigm, Montage pre-training, for object detection. Montage pre-training needs only the target detection dataset while taking only 1/4 computational resources compared to the…
Online video object segmentation is a challenging task as it entails to process the image sequence timely and accurately. To segment a target object through the video, numerous CNN-based methods have been developed by heavily finetuning on…
Affordance detection refers to identifying the potential action possibilities of objects in an image, which is a crucial ability for robot perception and manipulation. To empower robots with this ability in unseen scenarios, we first study…