Related papers: Human-Inspired Topological Representations for Vis…
This paper presents a topology-inspired morphological descriptor for soft continuum robots by combining a pseudo-rigid-body (PRB) model with Morse theory to achieve a quantitative characterization of robot morphologies. By counting critical…
Deep learning models have achieved remarkable success across various domains, yet their learned representations and decision-making processes remain largely opaque and hard to interpret. This work introduces HOLE (Homological Observation of…
We present T-Rex2, a highly practical model for open-set object detection. Previous open-set object detection methods relying on text prompts effectively encapsulate the abstract concept of common objects, but struggle with rare or complex…
We present a new approach to 3D object representation where a neural network encodes the geometry of an object directly into the weights and biases of a second 'mapping' network. This mapping network can be used to reconstruct an object by…
Achieving visual semantic understanding requires a unified framework that simultaneously handles object detection, category prediction, and attribute recognition. However, current advanced approaches rely on global similarity and struggle…
While today's robots are able to perform sophisticated tasks, they can only act on objects they have been trained to recognize. This is a severe limitation: any robot will inevitably see new objects in unconstrained settings, and thus will…
Deep-learning and large scale language-image training have produced image object detectors that generalise well to diverse environments and semantic classes. However, single-image object detectors trained on internet data are not optimally…
Over the past decade, significant progress has been made in visual object tracking, largely due to the availability of large-scale datasets. However, these datasets have primarily focused on open-air scenarios and have largely overlooked…
The area of Video Camouflaged Object Detection (VCOD) presents unique challenges in the field of computer vision due to texture similarities between target objects and their surroundings, as well as irregular motion patterns caused by both…
Recently, a number of competitive methods have tackled unsupervised representation learning by maximising the mutual information between the representations produced from augmentations. The resulting representations are then invariant to…
The tokenizer, as one of the fundamental components of large models, has long been overlooked or even misunderstood in visual tasks. One key factor of the great comprehension power of the large language model is that natural language…
Detection of objects in cluttered indoor environments is one of the key enabling functionalities for service robots. The best performing object detection approaches in computer vision exploit deep Convolutional Neural Networks (CNN) to…
Human-Object Interaction (HOI) detection is a task of identifying "a set of interactions" in an image, which involves the i) localization of the subject (i.e., humans) and target (i.e., objects) of interaction, and ii) the classification of…
To advance models of multimodal context, we introduce a simple yet powerful neural architecture for data that combines vision and natural language. The "Bounding Boxes in Text Transformer" (B2T2) also leverages referential information…
Recent advances in visual representation learning allowed to build an abundance of powerful off-the-shelf features that are ready-to-use for numerous downstream tasks. This work aims to assess how well these features preserve information…
Recent camouflaged object detection (COD) attempts to segment objects visually blended into their surroundings, which is extremely complex and difficult in real-world scenarios. Apart from the high intrinsic similarity between camouflaged…
Object proposal generation methods have been widely applied to many computer vision tasks. However, existing object proposal generation methods often suffer from the problems of motion blur, low contrast, deformation, etc., when they are…
Current Earth observation foundation models are architecturally rigid, struggle with heterogeneous sensors and are constrained to fixed patch sizes. This limits their deployment in real-world scenarios requiring flexible computeaccuracy…
Human visual perception offers valuable insights for understanding computational principles of motion-based scene interpretation. Humans robustly detect and segment moving entities that constitute independently moveable chunks of matter,…
Neural networks encode inputs as high-dimensional vectors, known as representations, that capture how models process data by encoding task-relevant structure and semantics. Representation alignment refers to the degree to which different…