Related papers: What and When to Look?: Temporal Span Proposal Net…
Recently, significant progresses have been made in object detection on common benchmarks (i.e., Pascal VOC). However, object detection in real world is still challenging due to the serious data imbalance. Images in real world are dominated…
Most Vision-and-Language Navigation (VLN) algorithms are prone to making inaccurate decisions due to their lack of visual common sense and limited reasoning capabilities. To address this issue, we propose a Hierarchical Spatial Proximity…
In visual place recognition (VPR), filtering and sequence-based matching approaches can improve performance by integrating temporal information across image sequences, especially in challenging conditions. While these methods are commonly…
Context has proven to be one of the most important factors in object layout reasoning for 3D scene understanding. Existing deep contextual models either learn holistic features for context encoding or rely on pre-defined scene templates for…
This thesis explores the central question of how to leverage temporal relations among video elements to advance video understanding. Addressing the limitations of existing methods, the work presents a five-fold contribution: (1) an…
Visual relationship detection aims to detect the interactions between objects in an image; however, this task suffers from combinatorial explosion due to the variety of objects and interactions. Since the interactions associated with the…
Visual relationship detection aims to locate objects in images and recognize the relationships between objects. Traditional methods treat all observed relationships in an image equally, which causes a relatively poor performance in the…
Visual Place Recognition (VPR) is the task of matching current visual imagery from a camera to images stored in a reference map of the environment. While initial VPR systems used simple direct image methods or hand-crafted visual features,…
Conventional approaches to video segmentation are confined to predefined object categories and cannot identify out-of-vocabulary objects, let alone objects that are not identified explicitly but only referred to implicitly in complex text…
Visual Place Recognition (VPR) in dynamic and perceptually aliased environments remains a fundamental challenge for long-term localization. Existing deep learning-based solutions predominantly focus on single-frame embeddings, neglecting…
Visual commonsense reasoning (VCR) is a challenging multi-modal task, which requires high-level cognition and commonsense reasoning ability about the real world. In recent years, large-scale pre-training approaches have been developed and…
Temporal sentence grounding (TSG) aims to localize the temporal segment which is semantically aligned with a natural language query in an untrimmed video.Most existing methods extract frame-grained features or object-grained features by 3D…
In this work, we address the problem of spatio-temporal action detection in temporally untrimmed videos. It is an important and challenging task as finding accurate human actions in both temporal and spatial space is important for analyzing…
Recognizing instances at different scales simultaneously is a fundamental challenge in visual detection problems. While spatial multi-scale modeling has been well studied in object detection, how to effectively apply a multi-scale…
In this paper we introduce ViSiL, a Video Similarity Learning architecture that considers fine-grained Spatio-Temporal relations between pairs of videos -- such relations are typically lost in previous video retrieval approaches that embed…
Deep convolutional networks have achieved great success for image recognition. However, for action recognition in videos, their advantage over traditional methods is not so evident. We present a general and flexible video-level framework…
We address the problem of retrieving a specific moment from an untrimmed video by natural language. It is a challenging problem because a target moment may take place in the context of other temporal moments in the untrimmed video. Existing…
We propose a novel method for temporally pooling frames in a video for the task of human action recognition. The method is motivated by the observation that there are only a small number of frames which, together, contain sufficient…
In this paper, we explore a novel task named visual Relation Grounding in Videos (vRGV). The task aims at spatio-temporally localizing the given relations in the form of subject-predicate-object in the videos, so as to provide supportive…
The crux of Referring Video Object Segmentation (RVOS) lies in modeling dense text-video relations to associate abstract linguistic concepts with dynamic visual contents at pixel-level. Current RVOS methods typically use vision and language…