Related papers: HookLens: Visual Analytics for Understanding React…

Human-Object Interaction (HOI) recognition is challenging due to two factors: (1) significant imbalance across classes and (2) requiring multiple labels per image. This paper shows that these two challenges can be effectively addressed by…

Human-Object Interaction (HOI) recognition is challenging due to two factors: (1) significant imbalance across classes and (2) requiring multiple labels per image. This paper shows that these two challenges can be effectively addressed by…

Interpretability is critical for machine learning models in high-stakes settings because it allows users to verify the model's reasoning. In computer vision, prototypical part models (ProtoPNets) have become the dominant model type to meet…

Modern code intelligence agents operate in contexts exceeding 1 million tokens--far beyond the scale where humans manually locate relevant files. Yet agents consistently fail to discover architecturally critical files when solving…

Human-object interaction (HOI) detection for capturing relationships between humans and objects is an important task in the semantic understanding of images. When processing human and object keypoints extracted from an image using a graph…

With the development of robotics, skeleton-based action recognition has become increasingly important, as human-robot interaction requires understanding the actions of humans and humanoid robots. Due to different sources of human skeletons…

To enable human oversight, agentic AI systems often provide a trace of reasoning and action steps. Designing traces to have an informative, but not overwhelming, level of detail remains a critical challenge. In three user studies on a…

Angular is one of the most widely adopted frameworks for developing large-scale, dynamic web applications. As projects increase in scope and complexity, developers face growing challenges in managing architecture and maintaining clean,…

GUI agents are rapidly shifting from multi-module pipelines to end-to-end, native vision-language models (VLMs) that perceive raw screenshots and directly interact with digital devices. Despite rapid progress on general GUI tasks, CAPTCHA…

Code localization--identifying precisely where in a codebase changes need to be made--is a fundamental yet challenging task in software maintenance. Existing approaches struggle to efficiently navigate complex codebases when identifying…

Foundation models have become central to unifying perception and planning in robotics, yet real-world deployment exposes a mismatch between their monolithic assumption that a single model can handle all cognitive functions and the…

Transforming a large language model (LLM) into a Vision-Language Model (VLM) can be achieved by mapping the visual tokens from a vision encoder into the embedding space of an LLM. Intriguingly, this mapping can be as simple as a shallow MLP…

Code clone detection is involved with detecting duplicated fragments of code within a code base. Detecting these clones is useful for maintenance operations which require editing the clones. The tools developed are expected to be robust…

We introduce VLM-Lens, a toolkit designed to enable systematic benchmarking, analysis, and interpretation of vision-language models (VLMs) by supporting the extraction of intermediate outputs from any layer during the forward pass of…

Dense action detection involves detecting multiple co-occurring actions while action classes are often ambiguous and represent overlapping concepts. We argue that handling the dual challenge of temporal and class overlaps is too complex to…

HOI detection has long been dominated by task-specific models, sometimes with early vision-language backbones such as CLIP. With the rise of large generative VLMs, a key question is whether standalone VLMs can perform HOI detection…

Despite their success, Large Vision-Language Models (LVLMs) remain vulnerable to hallucinations. While existing studies attribute the cause of hallucinations to insufficient visual attention to image tokens, our findings indicate that…

Visualizing narratives is useful to writers to reflect on unfinished drafts and identify unintentional biases and inconsistencies. Literary scholars can use the visualizations to identify nuanced patterns and literary styles from written…

We introduce algorithms to visualize feature spaces used by object detectors. The tools in this paper allow a human to put on `HOG goggles' and perceive the visual world as a HOG based object detector sees it. We found that these…

Patterns, which are collections of elements arranged in regular or near-regular arrangements, are an important graphic art form and widely used due to their elegant simplicity and aesthetic appeal. When a pattern is encoded as a flat image…