Related papers: IMPACT-Scribe: Interactive Temporal Action Segment…
Training a real-time gesture recognition model heavily relies on annotated data. However, manual data annotation is costly and demands substantial human effort. In order to address this challenge, we propose a framework that can…
Interactive segmentation aims to segment the specified target on the image with positive and negative clicks from users. Interactive ambiguity is a crucial issue in this field, which refers to the possibility of multiple compliant outcomes…
Due to the proliferation of short-form content and the rapid adoption of AI, opportunities for deep, reflective thinking have significantly diminished, undermining users' critical thinking and reducing engagement with the reasoning behind…
Interactive segmentation entails a human marking an image to guide how a model either creates or edits a segmentation. Our work addresses limitations of existing methods: they either only support one gesture type for marking an image (e.g.,…
This paper investigates the problem of impact-time-control and proposes a learning-based computational guidance algorithm to solve this problem. The proposed guidance algorithm is developed based on a general prediction-correction concept:…
Image registration is fundamental in medical imaging, enabling precise alignment of anatomical structures for diagnosis, treatment planning, image-guided interventions, and longitudinal monitoring. This work introduces IMPACT (Image Metric…
The quality of training data is critical to the performance of machine learning applications in domains like transportation, healthcare, and robotics. Accurate image labeling, however, often relies on time-consuming, expert-driven methods…
Machine learning has achieved remarkable success across a wide range of applications, yet many of its most effective methods rely on access to large amounts of labeled data or extensive online interaction. In practice, acquiring…
Deep learning models are the state-of-the-art methods for semantic point cloud segmentation, the success of which relies on the availability of large-scale annotated datasets. However, it can be extremely time-consuming and prohibitively…
Imitation learning enables robots to acquire complex manipulation skills from human demonstrations, but current methods rely solely on low-level sensorimotor data while ignoring the rich semantic knowledge humans naturally possess about…
In real-world sequential decision making tasks like autonomous driving, robotics, and healthcare, learning from observed state-action trajectories is critical for tasks like imitation, classification, and clustering. For example,…
Per-pixel masks of semantic objects are very useful in many applications, which, however, are tedious to be annotated. In this paper, we propose a human-agent collaborative annotation approach that can efficiently generate per-pixel masks…
Attribute-controlled translation (ACT) is a subtask of machine translation that involves controlling stylistic or linguistic attributes (like formality and gender) of translation outputs. While ACT has garnered attention in recent years due…
Robotic pick-and-place tasks in convenience stores pose challenges due to dense object arrangements, occlusions, and variations in object properties such as color, shape, size, and texture. These factors complicate trajectory planning and…
In the near future, more and more machines will perform tasks in the vicinity of human spaces or support them directly in their spatially bound activities. In order to simplify the verbal communication and the interaction between robotic…
Manual annotation of medical images is a labor-intensive and time-consuming process, posing a significant bottleneck in the development and deployment of robust medical imaging AI systems. This paper introduces a novel hands-free Human-AI…
Due to the difficulty of acquiring large-scale explicit user feedback, implicit feedback (e.g., clicks or other interactions) is widely applied as an alternative source of data, where user-item interactions can be modeled as a bipartite…
Deep learning models often achieve high performance by inadvertently learning spurious correlations between targets and non-essential features. For example, an image classifier may identify an object via its background that spuriously…
This paper presents SPIE: a novel approach for semantic and structural post-training of instruction-based image editing diffusion models, addressing key challenges in alignment with user prompts and consistency with input images. We…
Visual planning asks a model to generate the remaining steps of a procedure in natural language given a partial video context and a goal. Progress on this task is bottlenecked by annotation: clean labeled datasets are small, domain-narrow,…