Related papers: SCoRD: Subject-Conditional Relation Detection with…

Scene graph generation (SGG) analyzes images to extract meaningful information about objects and their relationships. In the dynamic visual world, it is crucial for AI systems to continuously detect new objects and establish their…

Detection of rare objects (e.g., traffic cones, traffic barrels and traffic warning triangles) is an important perception task to improve the safety of autonomous driving. Training of such models typically requires a large number of…

This paper introduces self-taught object localization, a novel approach that leverages deep convolutional networks trained for whole-image recognition to localize objects in images without additional human supervision, i.e., without using…

Compositional image retrieval (CIR) is a multimodal learning task where a model combines a query image with a user-provided text modification to retrieve a target image. CIR finds applications in a variety of domains including product…

In-context reinforcement learning (ICRL) is an emerging RL paradigm where an agent, after pretraining, can adapt to out-of-distribution test tasks without any parameter updates, instead relying on an expanding context of interaction…

Humans do not memorize everything. Thus, humans recognize scene changes by exploring the past images. However, available past (i.e., reference) images typically represent nearby viewpoints of the present (i.e., query) scene, rather than the…

Prompt tuning with large-scale pretrained vision-language models empowers open-vocabulary predictions trained on limited base categories, e.g., object classification and detection. In this paper, we propose compositional prompt tuning with…

Accurate and effective 3D object detection is critical for ensuring the driving safety of autonomous vehicles. Recently, state-of-the-art two-stage 3D object detectors have exhibited promising performance. However, these methods refine…

Composed image retrieval (CIR) is the task of retrieving specific images by using a query that involves both a reference image and a relative caption. Most existing CIR models adopt the late-fusion strategy to combine visual and language…

Scene graph generation has received growing attention with the advancements in image understanding tasks such as object detection, attributes and relationship prediction,~\etc. However, existing datasets are biased in terms of object and…

Occluded person re-identification (ReID) aims to match occluded person images to holistic ones across dis-joint cameras. In this paper, we propose a novel framework by learning high-order relation and topology information for discriminative…

Due to the fact that it is prohibitively expensive to completely annotate visual relationships, i.e., the (obj1, rel, obj2) triplets, relationship models are inevitably biased to object classes of limited pairwise patterns, leading to poor…

Our world can be succinctly and compactly described as structured scenes of objects and relations. A typical room, for example, contains salient objects such as tables, chairs and books, and these objects typically relate to each other by…

We propose an approach to predict the 3D shape and pose for the objects present in a scene. Existing learning based methods that pursue this goal make independent predictions per object, and do not leverage the relationships amongst them.…

Embeddings are an important tool for the representation of word meaning. Their effectiveness rests on the distributional hypothesis: words that occur in the same context carry similar semantic information. Here, we adapt this approach to…

Contrastive self-supervised learning has largely narrowed the gap to supervised pre-training on ImageNet. However, its success highly relies on the object-centric priors of ImageNet, i.e., different augmented views of the same image…

Research in scene graph generation has quickly gained traction in the past few years because of its potential to help in downstream tasks like visual question answering, image captioning, etc. Many interesting approaches have been proposed…

To determine if a skill can be executed in any given environment, a robot needs to learn the preconditions for the skill. As robots begin to operate in dynamic and unstructured environments, precondition models will need to generalize to…

Recently, with the prevalence of large-scale image dataset, the co-occurrence information among classes becomes rich, calling for a new way to exploit it to facilitate inference. In this paper, we propose Obj-GloVe, a generic scene-based…

The presence of occlusions has provided substantial challenges to typically-powerful object recognition algorithms. Additional sources of information can be extremely valuable to reduce errors caused by occlusions. Scene context is known to…