Related papers: RefCrowd: Grounding the Target in Crowd with Refer…

Cognitive computing systems require human labeled data for evaluation, and often for training. The standard practice used in gathering this data minimizes disagreement between annotators, and we have found this results in data that fails to…

Semi-supervised crowd analysis is a prominent area of research, as unlabeled data are typically abundant and inexpensive to obtain. However, traditional point-based annotations constrain performance because individual regions are inherently…

Referring expression comprehension (REC) aims to localize the target object described by a natural language expression. Recent advances in vision-language learning have led to significant performance improvements in REC tasks. However,…

This is a technical report for the GigaCrowd challenge. Reconstructing 3D crowds from monocular images is a challenging problem due to mutual occlusions, server depth ambiguity, and complex spatial distribution. Since no large-scale 3D…

Crowd counting is a concerned and challenging task in computer vision. Existing density map based methods excessively focus on the individuals' localization which harms the crowd counting performance in highly congested scenes. In addition,…

Referring Expression Comprehension (REC) aims to localize the target objects specified by free-form natural language descriptions in images. While state-of-the-art methods achieve impressive performance, they perform a dense perception of…

Referring expression comprehension (REC) and segmentation (RES) are two highly-related tasks, which both aim at identifying the referent according to a natural language expression. In this paper, we propose a novel Multi-task Collaborative…

We raise and define a new crowdsourcing scenario, open set crowdsourcing, where we only know the general theme of an unfamiliar crowdsourcing project, and we don't know its label space, that is, the set of possible labels. This is still a…

Referring image segmentation segments an image from a language expression. With the aim of producing high-quality masks, existing methods often adopt iterative learning approaches that rely on RNNs or stacked attention layers to refine…

Crowd counting is a fundamental problem in crowd analysis which is typically accomplished by estimating a crowd density map and summing over the density values. However, this approach suffers from background noise accumulation and loss of…

Referring expression comprehension aims to localize objects identified by natural language descriptions. This is a challenging task as it requires understanding of both visual and language domains. One nature is that each object can be…

In this paper, we are tackling the weakly-supervised referring expression grounding task, for the localization of a referent object in an image according to a query sentence, where the mapping between image regions and queries are not…

We address the problem of image-based crowd counting. In particular, we propose a new problem called unlabeled scene-adaptive crowd counting. Given a new target scene, we would like to have a crowd counting model specifically adapted to…

Using natural language to query visual information is a fundamental need in real-world applications. Text-Image Retrieval (TIR) retrieves a target image from a gallery based on an image-level description, while Referring Expression…

Human detection has witnessed impressive progress in recent years. However, the occlusion issue of detecting human in highly crowded environments is far from solved. To make matters worse, crowd scenarios are still under-represented in…

The outcome of a collective decision-making process, such as crowdsourcing, often relies on the procedure through which the perspectives of its individual members are aggregated. Popular aggregation methods, such as the majority rule, often…

Crowd counting has important applications in public safety and pandemic control. A robust and practical crowd counting system has to be capable of continuously learning with the new incoming domain data in real-world scenarios instead of…

Cloth-changing person Re-IDentification (Re-ID) is a particularly challenging task, suffering from two limitations of inferior discriminative features and limited training samples. Existing methods mainly leverage auxiliary information to…

Person re-identification faces two core challenges: precisely locating the foreground target while suppressing background noise and extracting fine-grained features from the target region. Numerous visual-only approaches address these…

Fine-grained text-to-image retrieval aims to retrieve a fine-grained target image with a given text query. Existing methods typically assume that each training image is accurately depicted by its textual descriptions. However, textual…