相关论文: ReSpec: Relevance and Specificity Grounded Online …

Enabling robots to learn novel visuomotor skills in a data-efficient manner remains an unsolved problem with myriad challenges. A popular paradigm for tackling this problem is through leveraging large unlabeled datasets that have many…

Social media platforms are a rich source of information these days, however, of all the available information, only a small fraction is of users' interest. To help users catch up with the latest topics of their interests from the large…

Stereo video retargeting aims to resize an image to a desired aspect ratio. The quality of retargeted videos can be significantly impacted by the stereo videos spatial, temporal, and disparity coherence, all of which can be impacted by the…

The proliferation of textual data on the Internet presents a unique opportunity for institutions and companies to monitor public opinion about their services and products. Given the rapid generation of such data, the text stream mining…

Recurrent Neural Networks are showing much promise in many sub-areas of natural language processing, ranging from document classification to machine translation to automatic question answering. Despite their promise, many recurrent models…

The vast majority of textual content is unstructured, making automated classification an important task for many applications. The goal of text classification is to automatically classify text documents into one or more predefined…

The task of video grounding, which temporally localizes a natural language description in a video, plays an important role in understanding videos. Existing studies have adopted strategies of sliding window over the entire video or…

Real-time video surveillance has become a crucial technology for smart cities, made possible through the large-scale deployment of mobile and fixed video cameras. In this paper, we propose situation-aware streaming, for real-time…

Capturing and processing video is increasingly common as cameras become cheaper to deploy. At the same time, rich video understanding methods have progressed greatly in the last decade. As a result, many organizations now have massive…

Video segmentation aims to segment and track every pixel in diverse scenarios accurately. In this paper, we present Tube-Link, a versatile framework that addresses multiple core tasks of video segmentation with a unified architecture. Our…

Event mentions in text correspond to real-world events of varying degrees of granularity. The task of subevent detection aims to resolve this granularity issue, recognizing the membership of multi-granular events in event complexes. Since…

Instruction tuning has been proven effective in enhancing zero-shot generalization across various tasks and in improving the performance of specific tasks. For task-specific improvements, strategically selecting and training on related…

A server, which is to keep track of heavy document traffic, is unable to filter the documents that are most relevant and updated for continuous text search queries. This paper focuses on handling continuous text extraction sustaining high…

Continual learning, the setting where a learning agent is faced with a never ending stream of data, continues to be a great challenge for modern machine learning systems. In particular the online or "single-pass through the data" setting…

Online contextual reasoning and association across consecutive video frames are critical to perceive instances in visual tracking. However, most current top-performing trackers persistently lean on sparse temporal relationships between…

In this paper, we explore the spatial redundancy in video recognition with the aim to improve the computational efficiency. It is observed that the most informative region in each frame of a video is usually a small image patch, which…

Deep learning video analytic systems process live video feeds from multiple cameras with computer vision models deployed on edge or cloud. To optimize utility for these systems, which usually corresponds to query accuracy, efficient…

Residual networks (ResNets) represent a powerful type of convolutional neural network (CNN) architecture, widely adopted and used in various tasks. In this work we propose an improved version of ResNets. Our proposed improvements address…

Retrieval-Augmented Generation (RAG) enhances large language models (LLMs) by integrating up-to-date external knowledge, yet real-world web environments present unique challenges. These limitations manifest as two key challenges: pervasive…

Traditional video reasoning segmentation methods rely on supervised fine-tuning, which limits generalization to out-of-distribution scenarios and lacks explicit reasoning. To address this, we propose \textbf{VideoSeg-R1}, the first…