Papers set matching
“set matching” 태그가 달린 논문 41편 · 필터 해제
CoMatcher: Multi-View Collaborative Feature Matching
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 matchingEfficient Building Roof Type Classification: A Domain-Specific Self-Supervised Approach
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 matchingDecoupling Semantic Similarity from Spatial Alignment for Neural Networks
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 matchingMultimodal Alignment of Histopathological Images Using Cell Segmentation and Point Set Matching for Integrative Cancer Analysis
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 matchingESM+: Modern Insights into Perspective on Text-to-SQL Evaluation in the Age of Large Language Models
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-SQLScaling Manipulation Learning with Visual Kinematic Chain Prediction
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 matchingNeural Slot Interpreters: Grounding Object Semantics in Emergent Slot Representations
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+4Arbitrary point cloud upsampling via Dual Back-Projection Network
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 matchingSketch-based Video Object Localization
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 matchingGeneralization Bounds for Set-to-Set Matching with Negative Sampling
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 matchingFrom Semi-supervised to Omni-supervised Room Layout Estimation Using Point Clouds
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 matchingHyRSM++: Hybrid Relation Guided Temporal Set Matching for Few-shot Action Recognition
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+2Learning Object-Language Alignments for Open-Vocabulary Object Detection
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+3DETRs with Collaborative Hybrid Assignments Training
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 matchingNormalised clustering accuracy: An asymmetric external cluster validity measure
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 matchingDETRs with Hybrid Matching
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 matchingAO2-DETR: Arbitrary-Oriented Object Detection Transformer
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+3Hybrid Relation Guided Set Matching for Few-shot Action Recognition
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 matchingMatching Feature Sets for Few-Shot Image Classification
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+1Temporal Complementarity-Guided Reinforcement Learning for Image-to-Video Person Re-Identification
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