Related papers: Reading Relevant Feature from Global Representatio…

It has been observed that visual classification models often rely mostly on the image background, neglecting the foreground, which hurts their robustness to distribution changes. To alleviate this shortcoming, we propose to monitor the…

This paper proposes a novel memory-based online video representation that is efficient, accurate and predictive. This is in contrast to prior works that often rely on computationally heavy 3D convolutions, ignore actual motion when aligning…

Locating an object in a sequence of frames, given its appearance in the first frame of the sequence, is a hard problem that involves many stages. Usually, state-of-the-art methods focus on bringing novel ideas in the visual encoding or…

It remains a huge challenge to design effective and efficient trackers under complex scenarios, including occlusions, illumination changes and pose variations. To cope with this problem, a promising solution is to integrate the temporal…

Most efforts in interpreting neural relevance models have focused on local explanations, which explain the relevance of a document to a query but are not useful in predicting the model's behavior on unseen query-document pairs. We propose a…

Dense point tracking is a challenging task requiring the continuous tracking of every point in the initial frame throughout a substantial portion of a video, even in the presence of occlusions. Traditional methods use optical flow models to…

Robot localization is a fundamental component of autonomous navigation in unknown environments. Among various sensing modalities, visual input from cameras plays a central role, enabling robots to estimate their position by tracking point…

Video retrieval using natural language queries has attracted increasing interest due to its relevance in real-world applications, from intelligent access in private media galleries to web-scale video search. Learning the cross-similarity of…

Recent advances in visual tracking showed that deep Convolutional Neural Networks (CNN) trained for image classification can be strong feature extractors for discriminative trackers. However, due to the drastic difference between image…

We propose a novel guided interactive segmentation (GIS) algorithm for video objects to improve the segmentation accuracy and reduce the interaction time. First, we design the reliability-based attention module to analyze the reliability of…

Visual Object tracking research has undergone significant improvement in the past few years. The emergence of tracking by detection approach in tracking paradigm has been quite successful in many ways. Recently, deep convolutional neural…

We present a method to accelerate global illumination computation in dynamic environments by taking advantage of limitations of the human visual system. A model of visual attention is used to locate regions of interest in a scene and to…

Tracking a point through a video can be a challenging task due to uncertainty arising from visual obfuscations, such as appearance changes and occlusions. Although current state-of-the-art discriminative models excel in regressing long-term…

Artificial objects usually have very stable shape features, which are stable, persistent properties in geometry. They can provide evidence for object recognition. Shape features are more stable and more distinguishing than appearance…

We consider the problem of video-based person re-identification. The goal is to identify a person from videos captured under different cameras. In this paper, we propose an efficient spatial-temporal attention based model for person…

Contextual information plays an important role in action recognition. Local operations have difficulty to model the relation between two elements with a long-distance interval. However, directly modeling the contextual information between…

Machine learning techniques are often used in computer vision due to their ability to leverage large amounts of training data to improve performance. Unfortunately, most generic object trackers are still trained from scratch online and do…

In recent years, deep-learning-based visual object trackers have been studied thoroughly, but handling occlusions and/or rapid motion of the target remains challenging. In this work, we argue that conditioning on the natural language (NL)…

In many computer vision tasks, the relevant information to solve the problem at hand is mixed to irrelevant, distracting information. This has motivated researchers to design attentional models that can dynamically focus on parts of images…

More powerful feature representations derived from deep neural networks benefit visual tracking algorithms widely. However, the lack of exploitation on temporal information prevents tracking algorithms from adapting to appearances changing…