相关论文: Precise Tool to Target Positioning Widgets (TOTTA)…

Weakly supervised object localization (WSOL) is a challenging task aiming to localize objects with only image-level supervision. Recent works apply visual transformer to WSOL and achieve significant success by exploiting the long-range…

Makeup plays a vital role in self-expression, identity, and confidence - yet remains an underexplored domain for assistive technology, especially for people with vision impairments. While existing tools support isolated tasks such as color…

Representational similarity in neural networks is inherently scale-dependent, yet widely used metrics such as Centered Kernel Alignment (CKA) and Procrustes analysis provide only global scalar estimates. These scalars often fail to…

3D object detection is crucial for applications like autonomous driving and robotics. However, in real-world environments, variations in sensor data distribution due to sensor upgrades, weather changes, and geographic differences can…

Test-Time Adaptation (TTA) for black-box models accessible only via APIs remains a largely unexplored challenge. Existing approaches such as post-hoc output refinement offer limited adaptive capacity, while Zeroth-Order Optimization (ZOO)…

Target disambiguation is crucial in resolving input ambiguity in augmented reality (AR), especially for queries over distant objects or cluttered scenes on the go. Yet, visual feedforward techniques that support this process remain…

Test-time alignment (TTA) aims to adapt models to specific rewards during inference. However, existing methods tend to either under-optimise or over-optimise (reward hack) the target reward function. We propose Null-Text Test-Time Alignment…

Finding a particular object in a display is important for viewers in many visualizations, for example, when reacting to brushing or to a highlighted object. This can be enabled by making the target object different in one of the visual…

Image-to-text tasks, such as open-ended image captioning and controllable image description, have received extensive attention for decades. Here, we further advance this line of work by presenting Visual Spatial Description (VSD), a new…

Existing vision-language models often suffer from spatial hallucinations, i.e., generating incorrect descriptions about the relative positions of objects in an image. We argue that this problem mainly stems from the asymmetric properties…

One of the most important challenges of Smart City Applications is to adapt the system to interact with non-expert users. Robot imitation frameworks aim to simplify and reduce times of robot programming by allowing users to program directly…

Test-Time adaptation (TTA) has proven effective in mitigating performance drops under single-domain distribution shifts by updating model parameters during inference. However, real-world deployments often involve mixed distribution shifts,…

The objective of this paper is to develop and evaluate a directional vibrotactile feedback interface as a guidance tool for postural adjustments during work. In contrast to the existing active and wearable systems such as exoskeletons, we…

Reinforcement learning (RL) fine-tuning has shown promise for Vision-Language-Action (VLA) models in robotic manipulation, but deployment-time visual shifts pose practical challenges. A key difficulty is that standard task rewards supervise…

Task-oriented dialogue (TOD) systems enable users to achieve their goals through natural language interactions. Traditionally, these systems have relied on turn-level manually annotated metadata, such as dialogue states and policy…

Semantic Image Segmentation facilitates a multitude of real-world applications ranging from autonomous driving over industrial process supervision to vision aids for human beings. These models are usually trained in a supervised fashion…

For many years, multi-object tracking benchmarks have focused on a handful of categories. Motivated primarily by surveillance and self-driving applications, these datasets provide tracks for people, vehicles, and animals, ignoring the vast…

Language models are often evaluated with scalar metrics like accuracy, but such measures fail to capture how models internally represent ambiguity, especially when human annotators disagree. We propose a topological perspective to analyze…

Adapting models to dynamic, real-world environments characterized by shifting data distributions and unseen test scenarios is a critical challenge in deep learning. In this paper, we consider a realistic and challenging Test-Time Adaptation…

This paper tackles a significant challenge faced by Vision Transformers (ViTs): their constrained scalability across different image resolutions. Typically, ViTs experience a performance decline when processing resolutions different from…