English
Related papers

Related papers: Rethinking Diversified and Discriminative Proposal…

200 papers

Conventional phrase grounding aims to localize noun phrases mentioned in a given caption to their corresponding image regions, which has achieved great success recently. Apparently, sole noun phrase grounding is not enough for cross-modal…

Computation and Language · Computer Science 2022-10-25 Panzhong Lu , Xin Zhang , Meishan Zhang , Min Zhang

Multimodal automatic speech recognition systems integrate information from images to improve speech recognition quality, by grounding the speech in the visual context. While visual signals have been shown to be useful for recovering…

Computation and Language · Computer Science 2020-10-07 Tejas Srinivasan , Ramon Sanabria , Florian Metze , Desmond Elliott

Existing methods for scene text detection can be divided into two paradigms: segmentation-based and anchor-based. While Segmentation-based methods are well-suited for irregular shapes, they struggle with compact or overlapping layouts.…

Computer Vision and Pattern Recognition · Computer Science 2024-02-20 Longhuang Wu , Shangxuan Tian , Youxin Wang , Pengfei Xiong

Post-training of language models, either through reinforcement learning, preference optimization or supervised finetuning, tends to sharpen the output probability distribution and reduce the diversity of generated responses. This is…

Computation and Language · Computer Science 2025-05-23 Jack Lanchantin , Angelica Chen , Shehzaad Dhuliawala , Ping Yu , Jason Weston , Sainbayar Sukhbaatar , Ilia Kulikov

Deep Convolutional Neural Networks (CNNs) have demonstrated excellent performance in image classification, but still show room for improvement in object-detection tasks with many categories, in particular for cluttered scenes and occlusion.…

Computer Vision and Pattern Recognition · Computer Science 2015-03-24 Nikolaos Karianakis , Thomas J. Fuchs , Stefano Soatto

Visual grounding in text-rich document images is a critical yet underexplored challenge for Document Intelligence and Visual Question Answering (VQA) systems. We present DRISHTIKON, a multi-granular and multi-block visual grounding…

Computer Vision and Pattern Recognition · Computer Science 2025-07-17 Badri Vishal Kasuba , Parag Chaudhuri , Ganesh Ramakrishnan

Textual grounding is an important but challenging task for human-computer interaction, robotics and knowledge mining. Existing algorithms generally formulate the task as selection from a set of bounding box proposals obtained from deep net…

Computer Vision and Pattern Recognition · Computer Science 2018-04-02 Raymond A. Yeh , Jinjun Xiong , Wen-mei W. Hwu , Minh N. Do , Alexander G. Schwing

We propose a learning system in which language is grounded in visual percepts without specific pre-defined categories of terms. We present a unified generative method to acquire a shared semantic/visual embedding that enables the learning…

Computation and Language · Computer Science 2021-08-02 Nisha Pillai , Cynthia Matuszek , Francis Ferraro

Current top performing object recognition systems build on object proposals as a preprocessing step. Object proposal algorithms are designed to generate candidate regions for generic objects, yet current approaches are limited in capturing…

Computer Vision and Pattern Recognition · Computer Science 2016-03-15 Anton Winschel , Rainer Lienhart , Christian Eggert

We introduce a framework for joint grounded scene graph - image generation, a challenging task involving high-dimensional, multi-modal structured data. To effectively model this complex joint distribution, we adopt a factorized approach:…

Computer Vision and Pattern Recognition · Computer Science 2025-08-05 Bicheng Xu , Qi Yan , Renjie Liao , Lele Wang , Leonid Sigal

Visual Place Recognition (VPR) has been traditionally formulated as a single-image retrieval task. Using multiple views offers clear advantages, yet this setting remains relatively underexplored and existing methods often struggle to…

Computer Vision and Pattern Recognition · Computer Science 2025-12-30 Tianchen Deng , Xun Chen , Ziming Li , Hongming Shen , Danwei Wang , Javier Civera , Hesheng Wang

Current state-of-the-art object proposal networks are trained with a closed-world assumption, meaning they learn to only detect objects of the training classes. These models fail to provide high recall in open-world environments where…

Computer Vision and Pattern Recognition · Computer Science 2024-04-18 Matthew Inkawhich , Nathan Inkawhich , Hai Li , Yiran Chen

Robust fine-tuning aims to adapt large foundation models to downstream tasks while preserving their robustness to distribution shifts. Existing methods primarily focus on constraining and projecting current model towards the pre-trained…

Machine Learning · Computer Science 2025-06-24 Chengyue Huang , Junjiao Tian , Brisa Maneechotesuwan , Shivang Chopra , Zsolt Kira

Visual grounding is a long-lasting problem in vision-language understanding due to its diversity and complexity. Current practices concentrate mostly on performing visual grounding in still images or well-trimmed video clips. This work, on…

Computer Vision and Pattern Recognition · Computer Science 2021-03-19 Qianyu Feng , Yunchao Wei , Mingming Cheng , Yi Yang

Personalized generative recommender systems have emerged as a promising solution for fashion recommendation. However, existing methods primarily rely on implicit visual embeddings from historical interactions, which often contain…

Information Retrieval · Computer Science 2026-05-19 Mingzhe Yu , Lei Wu , Qianru Sun , Yunshan Ma

Generating high-dimensional visual modalities is a computationally intensive task. A common solution is progressive generation, where the outputs are synthesized in a coarse-to-fine spectral autoregressive manner. While diffusion models…

Computer Vision and Pattern Recognition · Computer Science 2025-06-25 Moayed Haji-Ali , Willi Menapace , Ivan Skorokhodov , Arpit Sahni , Sergey Tulyakov , Vicente Ordonez , Aliaksandr Siarohin

Face detection is a widely studied problem over the past few decades. Recently, significant improvements have been achieved via the deep neural network, however, it is still challenging to directly apply these techniques to mobile devices…

Computer Vision and Pattern Recognition · Computer Science 2019-04-30 Heming Zhang , Xiaolong Wang , Jingwen Zhu , C. -C. Jay Kuo

Current top performing object detectors employ detection proposals to guide the search for objects, thereby avoiding exhaustive sliding window search across images. Despite the popularity and widespread use of detection proposals, it is…

Computer Vision and Pattern Recognition · Computer Science 2015-08-07 Jan Hosang , Rodrigo Benenson , Piotr Dollár , Bernt Schiele

Diffusion Probabilistic Field (DPF) models the distribution of continuous functions defined over metric spaces. While DPF shows great potential for unifying data generation of various modalities including images, videos, and 3D geometry, it…

Computer Vision and Pattern Recognition · Computer Science 2023-05-25 Kangfu Mei , Mo Zhou , Vishal M. Patel

Grounding referring expressions in RGBD image has been an emerging field. We present a novel task of 3D visual grounding in single-view RGBD image where the referred objects are often only partially scanned due to occlusion. In contrast to…

Computer Vision and Pattern Recognition · Computer Science 2021-03-18 Haolin Liu , Anran Lin , Xiaoguang Han , Lei Yang , Yizhou Yu , Shuguang Cui