Related papers: Inner-Scene Similarities as a Contextual Cue for O…
Humans can robustly recognize and localize objects by integrating visual and auditory cues. While machines are able to do the same now with images, less work has been done with sounds. This work develops an approach for dense semantic…
Evaluating object detection models in deployment is challenging because ground-truth annotations are rarely available. We introduce the Cumulative Consensus Score (CCS), a label-free monitoring signal for continuous evaluation and…
Recent progress on salient object detection mainly aims at exploiting how to effectively integrate convolutional side-output features in convolutional neural networks (CNN). Based on this, most of the existing state-of-the-art saliency…
A major goal of computer vision is to enable computers to interpret visual situations---abstract concepts (e.g., "a person walking a dog," "a crowd waiting for a bus," "a picnic") whose image instantiations are linked more by their common…
Generating an image from its textual description requires both a certain level of language understanding and common sense knowledge about the spatial relations of the physical entities being described. In this work, we focus on inferring…
Contextual information provides important cues for disambiguating visually similar pixels in scene segmentation. In this paper, we introduce a neuron-level Selective Context Aggregation (SCA) module for scene segmentation, comprised of a…
Depth estimation from a single image is a challenging problem in computer vision because binocular disparity or motion information is absent. Whereas impressive performances have been reported in this area recently using end-to-end trained…
Infrared small object detection (ISOS) aims to segment small objects only covered with several pixels from clutter background in infrared images. It's of great challenge due to: 1) small objects lack of sufficient intensity, shape and…
Collection of massive well-annotated samples is effective in improving object detection performance but is extremely laborious and costly. Instead of data collection and annotation, the recently proposed Cut-Paste methods [12, 15] show the…
Object recognition is an important problem in computer vision, having diverse applications. In this work, we construct an end-to-end scene recognition pipeline consisting of feature extraction, encoding, pooling and classification. Our…
Low-light conditions have an adverse impact on machine cognition, limiting the performance of computer vision systems in real life. Since low-light data is limited and difficult to annotate, we focus on image processing to enhance low-light…
Text-based person search aims at retrieving target person in an image gallery using a descriptive sentence of that person. It is very challenging since modal gap makes effectively extracting discriminative features more difficult. Moreover,…
Most existing person re-identification methods compute the matching relations between person images across camera views based on the ranking of the pairwise similarities. This matching strategy with the lack of the global viewpoint and the…
Recent works have widely explored the contextual dependencies to achieve more accurate segmentation results. However, most approaches rarely distinguish different types of contextual dependencies, which may pollute the scene understanding.…
With the proliferation of imaging sensors, the volume of multi-modal imagery far exceeds the ability of human analysts to adequately consume and exploit it. Full motion video (FMV) possesses the extra challenge of containing large amounts…
Diffusion-based re-ranking is a common method used for retrieving instances by performing similarity propagation in a nearest neighbor graph. However, existing techniques that construct the affinity graph based on pairwise instances can…
In-context learning$\unicode{x2013}$the ability to configure a model's behavior with different prompts$\unicode{x2013}$has revolutionized the field of natural language processing, alleviating the need for task-specific models and paving the…
By moving a depth sensor around a room, we compute a 3D CAD model of the environment, capturing the room shape and contents such as chairs, desks, sofas, and tables. Rather than reconstructing geometry, we match, place, and align each…
Dense captioning is a newly emerging computer vision topic for understanding images with dense language descriptions. The goal is to densely detect visual concepts (e.g., objects, object parts, and interactions between them) from images,…
In this paper, we present a framework for computing dense keypoint correspondences between images under strong scene appearance changes. Traditional methods, based on nearest neighbour search in the feature descriptor space, perform poorly…