paper-with-me

Papers set matching

“set matching” 태그가 달린 논문 41편 · 필터 해제

CoMatcher: Multi-View Collaborative Feature Matching

2025-04-02 · CVPR 2025 1 · Jintao Zhang, Zimin Xia, Mingyue Dong, Shuhan Shen 외

This paper proposes a multi-view collaborative matching strategy for reliable track construction in complex scenarios. We observe that the pairwise matching paradigms applied to image set matching often result in ambiguo…

Scene Understandingset matching

Efficient Building Roof Type Classification: A Domain-Specific Self-Supervised Approach

2025-03-28 · Guneet Mutreja, Ksenia Bittner

Accurate classification of building roof types from aerial imagery is crucial for various remote sensing applications, including urban planning, disaster management, and infrastructure monitoring. However, this task is o…

Computational EfficiencyContrastive LearningSelf-Supervised Learningset matching

Decoupling Semantic Similarity from Spatial Alignment for Neural Networks

2024-10-30 · Tassilo Wald, Constantin Ulrich, Gregor Köhler, David Zimmerer 외

What representation do deep neural networks learn? How similar are images to each other for neural networks? Despite the overwhelming success of deep learning methods key questions about their internal workings still rem…

Image RetrievalSemantic SimilaritySemantic Textual Similarityset matching

Multimodal Alignment of Histopathological Images Using Cell Segmentation and Point Set Matching for Integrative Cancer Analysis

2024-09-30 · Jun Jiang, Raymond Moore, Brenna Novotny, Leo Liu 외

Histopathological imaging is vital for cancer research and clinical practice, with multiplexed Immunofluorescence (MxIF) and Hematoxylin and Eosin (H&E) providing complementary insights. However, aligning different stain…

Cell SegmentationGraph Matchingset matching

ESM+: Modern Insights into Perspective on Text-to-SQL Evaluation in the Age of Large Language Models

2024-07-10 · Benjamin G. Ascoli, Yasoda Sai Ram Kandikonda, Jinho D. Choi

The task of Text-to-SQL enables anyone to retrieve information from SQL databases using natural language. Despite several challenges, recent models have made remarkable advancements in this task using large language mode…

set matchingText to SQLText-To-SQL

Scaling Manipulation Learning with Visual Kinematic Chain Prediction

2024-06-12 · Xinyu Zhang, YuHan Liu, Haonan Chang, Abdeslam Boularias

Learning general-purpose models from diverse datasets has achieved great success in machine learning. In robotics, however, existing methods in multi-task learning are typically constrained to a single robot and workspac…

Multi-Task LearningPredictionRobot Manipulationset matching

Neural Slot Interpreters: Grounding Object Semantics in Emergent Slot Representations

2024-02-02 · Bhishma Dedhia, Niraj K. Jha

Several accounts of human cognition posit that our intelligence is rooted in our ability to form abstract composable concepts, ground them in our environment, and reason over these grounded entities. This trifecta of hum…

Contrastive LearningObjectobject-detectionObject Detection+4

Arbitrary point cloud upsampling via Dual Back-Projection Network

2023-07-18 · Zhi-Song Liu, Zijia Wang, Zhen Jia

Point clouds acquired from 3D sensors are usually sparse and noisy. Point cloud upsampling is an approach to increase the density of the point cloud so that detailed geometric information can be restored. In this paper, …

point cloud upsamplingset matching

Sketch-based Video Object Localization

2023-04-02 · Sangmin Woo, So-Yeong Jeon, Jinyoung Park, Minji Son 외

We introduce Sketch-based Video Object Localization (SVOL), a new task aimed at localizing spatio-temporal object boxes in video queried by the input sketch. We first outline the challenges in the SVOL task and build the…

ObjectObject Localizationset matching

Generalization Bounds for Set-to-Set Matching with Negative Sampling

2023-02-25 · Masanari Kimura

The problem of matching two sets of multiple elements, namely set-to-set matching, has received a great deal of attention in recent years. In particular, it has been reported that good experimental results can be obtaine…

Generalization Boundsset matching

From Semi-supervised to Omni-supervised Room Layout Estimation Using Point Clouds

2023-01-31 · Huan-ang Gao, Beiwen Tian, Pengfei Li, Xiaoxue Chen 외

Room layout estimation is a long-existing robotic vision task that benefits both environment sensing and motion planning. However, layout estimation using point clouds (PCs) still suffers from data scarcity due to annota…

Motion PlanningPseudo LabelRoom Layout Estimationset matching

HyRSM++: Hybrid Relation Guided Temporal Set Matching for Few-shot Action Recognition

2023-01-09 · Xiang Wang, Shiwei Zhang, Zhiwu Qing, Zhengrong Zuo 외

Recent attempts mainly focus on learning deep representations for each video individually under the episodic meta-learning regime and then performing temporal alignment to match query and support videos. However, they st…

Action RecognitionFew-Shot action recognitionFew Shot Action RecognitionMeta-Learning+2

Learning Object-Language Alignments for Open-Vocabulary Object Detection

2022-11-27 · Chuang Lin, Peize Sun, Yi Jiang, Ping Luo 외

Existing object detection methods are bounded in a fixed-set vocabulary by costly labeled data. When dealing with novel categories, the model has to be retrained with more bounding box annotations. Natural language super…

Objectobject-detectionObject DetectionOpen-vocabulary object detection+3

DETRs with Collaborative Hybrid Assignments Training

2022-11-22 · ICCV 2023 1 · Zhuofan Zong, Guanglu Song, Yu Liu

In this paper, we provide the observation that too few queries assigned as positive samples in DETR with one-to-one set matching leads to sparse supervision on the encoder's output which considerably hurt the discriminat…

DecoderInstance SegmentationObject Detectionset matching

Normalised clustering accuracy: An asymmetric external cluster validity measure

2022-09-07 · Marek Gagolewski

There is no, nor will there ever be, single best clustering algorithm. Nevertheless, we would still like to be able to distinguish between methods that work well on certain task types and those that systematically underp…

Clusteringset matching

DETRs with Hybrid Matching

2022-07-26 · CVPR 2023 1 · Ding Jia, Yuhui Yuan, Haodi He, Xiaopei Wu 외

One-to-one set matching is a key design for DETR to establish its end-to-end capability, so that object detection does not require a hand-crafted NMS (non-maximum suppression) to remove duplicate detections. This end-to-…

Object DetectionPose EstimationSemantic Segmentationset matching

AO2-DETR: Arbitrary-Oriented Object Detection Transformer

2022-05-25 · Linhui Dai, Hong Liu, Hao Tang, Zhiwei Wu 외

Arbitrary-oriented object detection (AOOD) is a challenging task to detect objects in the wild with arbitrary orientations and cluttered arrangements. Existing approaches are mainly based on anchor-based boxes or dense p…

DecoderInductive BiasObjectobject-detection+3

Hybrid Relation Guided Set Matching for Few-shot Action Recognition

2022-04-28 · CVPR 2022 1 · Xiang Wang, Shiwei Zhang, Zhiwu Qing, Mingqian Tang 외

Current few-shot action recognition methods reach impressive performance by learning discriminative features for each video via episodic training and designing various temporal alignment strategies. Nevertheless, they ar…

Action RecognitionFew Shot Action RecognitionRelationset matching

Matching Feature Sets for Few-Shot Image Classification

2022-04-02 · CVPR 2022 1 · Arman Afrasiyabi, Hugo Larochelle, Jean-François Lalonde, Christian Gagné

In image classification, it is common practice to train deep networks to extract a single feature vector per input image. Few-shot classification methods also mostly follow this trend. In this work, we depart from this e…

ClassificationFew-Shot Image Classificationimage-classificationImage Classification+1

Temporal Complementarity-Guided Reinforcement Learning for Image-to-Video Person Re-Identification

2022-01-01 · CVPR 2022 1 · Wei Wu, Jiawei Liu, Kecheng Zheng, Qibin Sun 외

Image-to-video person re-identification aims to retrieve the same pedestrian as the image-based query from a video-based gallery set. Existing methods treat it as a cross-modality retrieval task and learn the common …

Deep Reinforcement LearningImage-To-Video Person Re-IdentificationPerson Re-Identificationreinforcement-learning+4
1–20 / 41 다음 →