Related papers: An Automated Approach to Reasoning About Task-Orie…
Image-text contrastive learning models such as CLIP have demonstrated strong task transfer ability. The high generality and usability of these visual models is achieved via a web-scale data collection process to ensure broad concept…
Dialog response ranking is used to rank response candidates by considering their relation to the dialog history. Although researchers have addressed this concept for open-domain dialogs, little attention has been focused on task-oriented…
Exponential growth in the quantity of digital news, social media, and other textual sources makes it difficult for humans to keep up with rapidly evolving narratives about world events. Various visualisation techniques have been touted to…
Data visualization should be accessible for all analysts with data, not just the few with technical expertise. Visualization recommender systems aim to lower the barrier to exploring basic visualizations by automatically generating results…
Multimodal Large Language Models have advanced AI in applications like text-to-video generation and visual question answering. These models rely on visual encoders to convert non-text data into vectors, but current encoders either lack…
We address the problem of visually guided rearrangement planning with many movable objects, i.e., finding a sequence of actions to move a set of objects from an initial arrangement to a desired one, while relying on visual inputs coming…
Active learning emerged as an alternative to alleviate the effort to label huge amount of data for data hungry applications (such as image/video indexing and retrieval, autonomous driving, etc.). The goal of active learning is to…
Optimizing application performance in today's hardware architecture landscape is an important, but increasingly complex task, often requiring detailed performance analyses. In particular, data movement and reuse play a crucial role in…
Passive tracking methods, such as phone and wearable sensing, have become dominant in monitoring human behaviors in modern ubiquitous computing studies. While there have been significant advances in machine-learning approaches to translate…
Data visualizations are powerful tools for communicating patterns in quantitative data. Yet understanding any data visualization is no small feat -- succeeding requires jointly making sense of visual, numerical, and linguistic inputs…
Visuomotor policies often suffer from perceptual challenges, where visual differences between training and evaluation environments degrade policy performance. Policies relying on state estimations, like 6D pose, require task-specific…
Visual place recognition is a critical task in computer vision, especially for localization and navigation systems. Existing methods often rely on contrastive learning: image descriptors are trained to have small distance for similar images…
User experience in data visualization is typically assessed through post-viewing self-reports, but these overlook the dynamic cognitive processes during interaction. This study explores the use of mind wandering -- a phenomenon where…
Recommender system exists everywhere in the business world. From Goodreads to TikTok, customers of internet products become more addicted to the products thanks to the technology. Industrial practitioners focus on increasing the technical…
Many tasks in computer vision are often calibrated and evaluated relative to human perception. In this paper, we propose to directly approximate the perceptual function performed by human observers completing a visual detection task.…
In this paper, the main task we aim to tackle is the multi-instance semi-supervised video object segmentation across a sequence of frames where only the first-frame box-level ground-truth is provided. Detection-based algorithms are widely…
Industrial-scale recommender systems rely on a cascade pipeline in which the retrieval stage must return a high-recall candidate set from billions of items under tight latency. Existing solutions either (i) suffer from limited…
Visual object localization is the key step in a series of object detection tasks. In the literature, high localization accuracy is achieved with the mainstream strongly supervised frameworks. However, such methods require object-level…
Reference resolution, which aims to identify entities being referred to by a speaker, is more complex in real world settings: new referents may be created by processes the agents engage in and/or be salient only because they belong to the…
The task of rationalization aims to extract pieces of input text as rationales to justify neural network predictions on text classification tasks. By definition, rationales represent key text pieces used for prediction and thus should have…