Related papers: Do Vision Models Encode Object-Level Semantic Rela…

Category-level pose estimation is a challenging task with many potential applications in computer vision and robotics. Recently, deep-learning-based approaches have made great progress, but are typically hindered by the need for large…

This survey examines multilingual vision-language models that process text and images across languages. We review 33 models and 23 benchmarks, spanning encoder-only and generative architectures, and identify a key tension between language…

Semantic segmentation has made significant strides in pixel-level image understanding, yet it remains limited in capturing contextual and semantic relationships between objects. Current models, such as CNN and Transformer-based…

Visual reasoning is critical for a wide range of computer vision tasks that go beyond surface-level object detection and classification. Despite notable advances in relational, symbolic, temporal, causal, and commonsense reasoning, existing…

In this paper, we are interested in understanding self-supervised pretraining through studying the capability that self-supervised representation pretraining methods learn part-aware representations. The study is mainly motivated by that…

Self-supervised representation learning for visual pre-training has achieved remarkable success with sample (instance or pixel) discrimination and semantics discovery of instance, whereas there still exists a non-negligible gap between…

Vision-language models (VLMs) excel at broad visual understanding but remain coarse-grained, exhibit visual biases, and miss subtle visual details. Existing training corpora reinforce this limitation by emphasizing general recognition ("Is…

Monocular 3D object detection typically relies on pseudo-labeling techniques to reduce dependency on real-world annotations. Recent advances demonstrate that deterministic linguistic cues can serve as effective auxiliary weak supervision…

Encoding models have as their objective to predict neural responses to naturalistic stimuli with the aim of elucidating how sensory information is represented in the brain. This prediction is achieved by representing the stimulus in terms…

Large Vision-Language Models (LVLMs) usually suffer from prohibitive computational and memory costs due to the quadratic growth of visual tokens with image resolution. Existing token compression methods, while varied, often lack a…

The words of a language reflect the structure of the human mind, allowing us to transmit thoughts between individuals. However, language can represent only a subset of our rich and detailed cognitive architecture. Here, we ask what kinds of…

The ambiguity between generalization and memorization in TTI diffusion models becomes pronounced when prompts invoke culturally shared visual references, a phenomenon we term multimodal iconicity. These are instances in which images and…

Visual understanding requires comprehending complex visual relations between objects within a scene. Here, we seek to characterize the computational demands for abstract visual reasoning. We do this by systematically assessing the ability…

Vision-Language Models (VLMs) have demonstrated impressive world knowledge across a wide range of tasks, making them promising candidates for embodied reasoning applications. However, existing benchmarks primarily evaluate the embodied…

This paper investigates contextual word representation models from the lens of similarity analysis. Given a collection of trained models, we measure the similarity of their internal representations and attention. Critically, these models…

Compositional generalization, the ability to reason about novel combinations of familiar concepts, is fundamental to human cognition and a critical challenge for machine learning. Object-centric (OC) representations, which encode a scene as…

The aim of this paper is threefold. We inform the AI practitioner about the human visual system with an extensive literature review; we propose a novel biologically motivated neural network for image classification; and, finally, we present…

Single object tracking aims to locate one specific target in video sequences, given its initial state. Classical trackers rely solely on visual cues, restricting their ability to handle challenges such as appearance variations, ambiguity,…

Humans represent scenes and objects in rich feature spaces, carrying information that allows us to generalise about category memberships and abstract functions with few examples. What determines whether a neural network model generalises…

Visual grounding is a task to locate the target indicated by a natural language expression. Existing methods extend the generic object detection framework to this problem. They base the visual grounding on the features from pre-generated…