Related papers: Correspondence Matters for Video Referring Express…

Document-level relation extraction (RE) aims to identify relations between two entities in a given document. Compared with its sentence-level counterpart, document-level RE requires complex reasoning. Previous research normally completed…

Object detection and instance segmentation are two fundamental computer vision tasks. They are closely correlated but their relations have not yet been fully explored in most previous work. This paper presents RDSNet, a novel deep…

In this work we target the problem of estimating accurately localised correspondences between a pair of images. We adopt the recent Neighbourhood Consensus Networks that have demonstrated promising performance for difficult correspondence…

In this work, we present a novel learning-based framework that combines the local accuracy of contrastive learning with the global consistency of geometric approaches, for robust non-rigid matching. We first observe that while contrastive…

There has been significant attention to the research on dense video captioning, which aims to automatically localize and caption all events within untrimmed video. Several studies introduce methods by designing dense video captioning as a…

This paper addresses the challenge of dense pixel correspondence estimation between two images. This problem is closely related to optical flow estimation task where ConvNets (CNNs) have recently achieved significant progress. While optical…

Advances in deep learning techniques have allowed recent work to reconstruct the shape of a single object given only one RBG image as input. Building on common encoder-decoder architectures for this task, we propose three extensions: (1)…

Reference Expression Generation (REG) and Comprehension (REC) are two highly correlated tasks. Modeling REG and REC simultaneously for utilizing the relation between them is a promising way to improve both. However, the problem of distinct…

Untrimmed videos have interrelated events, dependencies, context, overlapping events, object-object interactions, domain specificity, and other semantics that are worth highlighting while describing a video in natural language. Owing to…

Despite recent progress, vision-language encoders struggle with two core limitations: (1) weak alignment between language and dense vision features, which hurts tasks like open-vocabulary semantic segmentation; and (2) high token counts for…

Modern supervised semantic segmentation methods are usually finetuned based on the supervised or self-supervised models pre-trained on ImageNet. Recent work shows that transferring the knowledge from CLIP to semantic segmentation via prompt…

Convolutional neural networks (CNN) have shown promising results for end-to-end speech recognition, albeit still behind other state-of-the-art methods in performance. In this paper, we study how to bridge this gap and go beyond with a novel…

Recent studies have increasingly acknowledged the advantages of incorporating visual data into speech enhancement (SE) systems. In this paper, we introduce a novel audio-visual SE approach, termed DCUC-Net (deep complex U-Net with conformer…

Video understanding has been considered as one critical step towards world modeling, which is an important long-term problem in AI research. Recently, multimodal foundation models have shown such potential via large-scale pretraining. These…

Segmenting primary objects in a video is an important yet challenging problem in computer vision, as it exhibits various levels of foreground/background ambiguities. To reduce such ambiguities, we propose a novel formulation via exploiting…

Cross-modal retrieval methods have been significantly improved in last years with the use of deep neural networks and large-scale annotated datasets such as ImageNet and Places. However, collecting and annotating such datasets requires a…

Referring expression comprehension aims to localize the object instance described by a natural language expression. Current referring expression methods have achieved good performance. However, none of them is able to achieve real-time…

3D Visual Grounding (3DVG) aims to localize the referent of natural language referring expressions through two core tasks: Referring Expression Comprehension (3DREC) and Segmentation (3DRES). While existing methods achieve high accuracy in…

Most recent work in goal oriented visual navigation resorts to large-scale machine learning in simulated environments. The main challenge lies in learning compact representations generalizable to unseen environments and in learning…

Geometric verification is considered a de facto solution for the re-ranking task in image retrieval. In this study, we propose a novel image retrieval re-ranking network named Correlation Verification Networks (CVNet). Our proposed network,…