1-100 of about 104 matches for site:arxiv.org site:arxiv.org category
https://arxiv.org/abs/2104.08418
2104.08418] FiG-NeRF: Figure-Ground Neural Radiance Fields for 3D Object Category Modelling Skip to main
[2403.10853] Just Say the Name: Online Continual Learning with Category Names Only via Data Generati
https://arxiv.org/abs/2403.10853
2403.10853] Just Say the Name: Online Continual Learning with Category Names Only via Data Generation Skip to
[2306.09109] NAVI: Category-Agnostic Image Collections with High-Quality 3D Shape and Pose Annotatio
https://arxiv.org/abs/2306.09109
2306.09109] NAVI: Category-Agnostic Image Collections with High-Quality 3D Shape and Pose Annotations Skip to
[2305.01618] ContactArt: Learning 3D Interaction Priors for Category-level Articulated Object and Ha
https://arxiv.org/abs/2305.01618
2305.01618] ContactArt: Learning 3D Interaction Priors for Category-level Articulated Object and Hand Poses Estimation Happy
https://arxiv.org/abs/2104.08418
2104.08418] FiG-NeRF: Figure-Ground Neural Radiance Fields for 3D Object Category Modelling Skip to main
[2305.01618] ContactArt: Learning 3D Interaction Priors for Category-level Articulated Object and Ha
https://arxiv.org/abs/2305.01618
2305.01618] ContactArt: Learning 3D Interaction Priors for Category-level Articulated Object and Hand Poses Estimation Skip
[2306.09109] NAVI: Category-Agnostic Image Collections with High-Quality 3D Shape and Pose Annotatio
https://arxiv.org/abs//2306.09109
2306.09109] NAVI: Category-Agnostic Image Collections with High-Quality 3D Shape and Pose Annotations Skip to
[2306.09109] NAVI: Category-Agnostic Image Collections with High-Quality 3D Shape and Pose Annotatio
https://arxiv.org/abs//2306.09109
2306.09109] NAVI: Category-Agnostic Image Collections with High-Quality 3D Shape and Pose Annotations Skip to
https://arxiv.org/abs/2505.20283
2505.20283] Category-Agnostic Neural Object Rigging Skip to main content We gratefully acknowledge support from the
[2206.15436] Category-Level 6D Object Pose Estimation in the Wild: A Semi-Supervised Learning Approa
https://arxiv.org/abs/2206.15436
made on generalizing pose estimation to novel object instances within the same category, namely category-level 6D
https://arxiv.org/abs/2505.20283
2505.20283] Category-Agnostic Neural Object Rigging Skip to main content We gratefully acknowledge support from the
[2206.15436] Category-Level 6D Object Pose Estimation in the Wild: A Semi-Supervised Learning Approa
https://arxiv.org/abs/2206.15436
made on generalizing pose estimation to novel object instances within the same category, namely category-level 6D
https://arxiv.org/abs/2412.05268
2412.05268] DenseMatcher: Learning 3D Semantic Correspondence for Category-Level Manipulation from a Single Demo Happy Open
[2104.03437] CAPTRA: CAtegory-level Pose Tracking for Rigid and Articulated Objects from Point Cloud
https://arxiv.org/abs/2104.03437
2104.03437] CAPTRA: CAtegory-level Pose Tracking for Rigid and Articulated Objects from Point Clouds Skip
https://arxiv.org/abs/1904.10340
10340] Introduction to Gestural Similarity in Music. An Application of Category Theory to the
https://arxiv.org/abs/2303.06163
2303.06163] Category-Level Multi-Part Multi-Joint 3D Shape Assembly Skip to main content We gratefully
[2210.07199] Self-Supervised Geometric Correspondence for Category-Level 6D Object Pose Estimation i
https://arxiv.org/abs/2210.07199
2210.07199] Self-Supervised Geometric Correspondence for Category-Level 6D Object Pose Estimation in the Wild
[2210.07199] Self-Supervised Geometric Correspondence for Category-Level 6D Object Pose Estimation i
https://arxiv.org/abs/2210.07199
2210.07199] Self-Supervised Geometric Correspondence for Category-Level 6D Object Pose Estimation in the Wild
https://arxiv.org/abs/2405.06903
2405.06903] UniGarmentManip: A Unified Framework for Category-Level Garment Manipulation via Dense Visual Correspondence Skip to
https://arxiv.org/abs/2304.14401
the encoded feature space, we will first align different human subjects in a category-level canonical space, and
https://arxiv.org/abs/2401.09416
views and accurately aligned geometry, while learning-based methods are confined to category-specific shapes within the
https://arxiv.org/abs/2303.04803
representations of both these models to perform panoptic segmentation of any category in the
https://arxiv.org/abs/2303.04803
representations of both these models to perform panoptic segmentation of any category in the
https://arxiv.org/abs/2401.09416
views and accurately aligned geometry, while learning-based methods are confined to category-specific shapes within the
https://arxiv.org/a/roberts_d_1.html
version to appear in NYJM---17 pages Subjects: Algebraic Topology (math.AT) ; Category Theory (math.CT) [2
https://arxiv.org/abs/2204.09222
the-art computer vision systems are trained from natural language supervision, ranging from simple object category names to descriptive
http://arxiv.org/abs/q-alg/9503002
and n-vector spaces. We review progress towards a definition of n-category suited for this
https://arxiv.org/abs/2204.09222
the-art computer vision systems are trained from natural language supervision, ranging from simple object category names to descriptive
http://arxiv.org/abs/math/0307263
a new notion of "2-vector space", which we define as an internal category in Vect
https://arxiv.org/abs/2307.13697
data. \textbf{4) External Knowledge Injection:} By fine-tuning special token embeddings for each category via Textual Inversion, performance
http://arxiv.org/abs/2011.04000
gives a user the flexibility to control the category and intensity
https://arxiv.org/
new , recent , search ) includes (see detailed description ): Algebraic Geometry ; Algebraic Topology ; Analysis of PDEs ; Category Theory ; Classical Analysis and
https://arxiv.org/abs/2110.00239
Full text Search open search GO open navigation menu quick links Login Help Pages About Mathematics > Category Theory arXiv:2110.00239
https://arxiv.org/abs/1602.04907
functor, in the sense of Kevin Walker, from any modular tensor category. We further show that
http://arxiv.org/abs/math/0307200
in which the underlying set G has been replaced by a category and the
https://arxiv.org/abs/2210.15909
the problem of knowledge transfer between two datasets with domain-shift as well as category-shift. The goal
https://arxiv.org/abs/1709.04494
transform instances of that category to equivalent instances of another category. Our system proceeds in
https://arxiv.org/abs/1808.04552
Full text Search open search GO open navigation menu quick links Login Help Pages About Mathematics > Category Theory arXiv:1808.04552
https://arxiv.org/abs/2406.00609
high quality Gaussian Splat models, which are object centric and effective. Our method is category agnostic and can
https://arxiv.org/abs/1512.02325
the network generates scores for the presence of each object category in each
https://arxiv.org/abs/2311.04400
methods that are trained on small-scale datasets such as ShapeNet in a category-specific fashion, LRM adopts
https://arxiv.org/abs/2311.04400
methods that are trained on small-scale datasets such as ShapeNet in a category-specific fashion, LRM adopts
https://arxiv.org/abs/2204.02320
learn dexterous manipulation using large-scale demonstrations with diverse 3D objects in a category, which are generated from
https://arxiv.org/abs/1905.04804
YouTube-VIS, which consists of 2883 high-resolution YouTube videos, a 40-category label set and
https://arxiv.org/abs/2204.02320
learn dexterous manipulation using large-scale demonstrations with diverse 3D objects in a category, which are generated from
https://arxiv.org/abs/math/9910006
Full text Search open search GO open navigation menu quick links Login Help Pages About Mathematics > Category Theory arXiv:math/9910006
https://arxiv.org/abs/1302.7019
lift the construction to a bigroupoid internal to the category of topological
https://arxiv.org/abs/1602.07973
Full text Search open search GO open navigation menu quick links Login Help Pages About Mathematics > Category Theory arXiv:1602.07973
https://arxiv.org/abs/1508.07789
Full text Search open search GO open navigation menu quick links Login Help Pages About Mathematics > Category Theory arXiv:1508.07789
http://arxiv.org/abs/1402.7108
Full text Search open search GO open navigation menu quick links Login Help Pages About Mathematics > Category Theory arXiv:1402.7108
https://arxiv.org/abs/0904.0125
Full text Search open search GO open navigation menu quick links Login Help Pages About Mathematics > Category Theory arXiv:0904.0125
https://arxiv.org/abs/2204.02778
of topological stacks of categories, taking values in the 2-category of spaces
http://arxiv.org/abs/0905.0465
Full text Search open search GO open navigation menu quick links Login Help Pages About Mathematics > Category Theory arXiv:0905.0465
https://arxiv.org/abs/1203.2460
a product-preserving classifying space functor for groups in the category of spaces
https://arxiv.org/abs/2010.10325
2 other authors View PDF Abstract: We explain how to reconstruct the category of Artin
[2311.08514] An algorithm for Tambara-Yamagami quantum invariants of 3-manifolds, parameterized by t
https://arxiv.org/abs/2311.08514
state sum construction, which uses the data of a spherical fusion category to define
https://arxiv.org/abs/2010.10325
2 other authors View PDF Abstract: We explain how to reconstruct the category of Artin
https://arxiv.org/abs/1911.01238
means of a vector potential? Furthermore, it also turns out that the category of distributed
https://arxiv.org/abs/q-alg/9503002v2
and n-vector spaces. We review progress towards a definition of n-category suited for this
https://arxiv.org/abs/2401.12592
channel allows better 3D annotations and broader downstream applications. WildRGB-D comprises large-scale category-level RGB-D object
https://arxiv.org/abs/2311.17776
Learning (OOAL), where a model is trained with just one example per base object category, but is expected to
https://arxiv.org/abs/2303.16201
of sparse in-the-wild image collections of an object category. Most prior works assume
https://arxiv.org
new , recent , search ) includes: (see detailed description ): Algebraic Geometry ; Algebraic Topology ; Analysis of PDEs ; Category Theory ; Classical Analysis and
https://arxiv.org/abs/2401.12592
channel allows better 3D annotations and broader downstream applications. WildRGB-D comprises large-scale category-level RGB-D object
https://arxiv.org/abs/1204.1286
anomalies has increased. An important change is the emergence of a category of summertime
[hep-th/9405183] Four dimensional topological quantum field theory, Hopf categories, and the canonic
http://arxiv.org/abs/hep-th/9405183
uses a new type of algebraic structure called a Hopf Category. We also outline the
http://arxiv.org/abs/hep-th/9301062
construct a four dimensional topological Quantum Field Theory from a modular tensor category. We complete the
https://arxiv.org/abs/1610.05904
the 2016 MATRIX Annals ( this https URL ), 6 pages, comments welcome Subjects: Differential Geometry (math.DG) ; Category Theory (math.CT) MSC
https://arxiv.org/abs/1411.5779
comments. Released under a CC0 license ( this http URL ) Subjects: Algebraic Topology (math.AT) ; Category Theory (math.CT) MSC
https://arxiv.org/abs/1506.07931
welcome. License is CC-BY Subjects: Differential Geometry (math.DG) ; High Energy Physics - Theory (hep-th); Category Theory (math.CT) MSC
https://arxiv.org/abs/1702.01514
Theory Subjects: Differential Geometry (math.DG) ; High Energy Physics - Theory (hep-th); Mathematical Physics (math-ph); Category Theory (math.CT) Cite
https://arxiv.org/abs/2207.10617
particular, we propose training losses to exploit hyperlinks, article structures, and article category graphs for entity
http://arxiv.org/abs/hep-th/9212115
topological theory the path integral over the circle is the category of representations
https://arxiv.org/abs/2209.05521
pages+19 pages appendices+3 pages refs Subjects: Differential Geometry (math.DG) ; Mathematical Physics (math-ph); Category Theory (math.CT) MSC
http://arxiv.org/abs/hep-th/0509163
M5-brane systems, to spinning strings and to the derived category description of D
http://arxiv.org/abs/hep-th/9308126
The construction avoids path integrals, using instead recombination diagrams in a certain tensor category. Comments: 10 pages to
https://arxiv.org/abs/1204.3216
invertible. This paper introduces a categorical construction of musical transformations based on category extensions using groupoids. This
http://arxiv.org/archive/cs
including also robustness, explanation, fairness, and methodology. cs.LG is also an appropriate primary category for applications
https://arxiv.org/abs/2502.09328
preference across programming languages yet significant variation in preference due to task category. We open-source Copilot
https://arxiv.org/abs/2101.05870
than average. Several psychiatric conditions such as schizophrenia and autism also fall into this category. We discuss related topics
https://arxiv.org/abs/2306.06513
restoration. Instead of learning a single codebook for each image category, we learn a
https://arxiv.org/abs/2012.04512
for an active agent to navigate to a specified target object category in an
https://arxiv.org/abs/2502.09328
preference across programming languages yet significant variation in preference due to task category. We open-source Copilot
[cs/0312059] Polyhierarchical Classifications Induced by Criteria Polyhierarchies, and Taxonomy Alge
http://arxiv.org/abs/cs/0312059
of general persistent polyhierarchical classifications is proposed. It is based on implicit description of category polyhierarchy by a
[2209.03320] What does a platypus look like? Generating customized prompts for zero-shot image class
https://arxiv.org/abs/2209.03320
photo of a {}") which are completed with each of the category names. This work introduces
https://arxiv.org/abs/2311.11666
is accomplished by two steps. Firstly, we design a novel hierarchical representation based on category-agnostic 2D segmentations to
https://arxiv.org/abs/2010.09869
understanding of the second extended power functor in PstrÄ…gowski's category of synthetic
[2211.09423] DexPoint: Generalizable Point Cloud Reinforcement Learning for Sim-to-Real Dexterous Ma
https://arxiv.org/abs/2211.09423
dexterous manipulation which can generalize to new objects of the same category in the
https://arxiv.org/abs/2010.09869
understanding of the second extended power functor in PstrÄ…gowski's category of synthetic
https://arxiv.org/abs/1912.13411
use mathematics, and in particular the abstract branch of category theory, to describe
https://arxiv.org/abs/2306.06513
restoration. Instead of learning a single codebook for each image category, we learn a
[2211.09423] DexPoint: Generalizable Point Cloud Reinforcement Learning for Sim-to-Real Dexterous Ma
https://arxiv.org/abs/2211.09423
dexterous manipulation which can generalize to new objects of the same category in the
https://arxiv.org/abs/2311.11666
is accomplished by two steps. Firstly, we design a novel hierarchical representation based on category-agnostic 2D segmentations to
https://arxiv.org/abs/1811.06670
authors View PDF Abstract: In this paper we provide an overview of category theory, focussing on applications
https://arxiv.org/abs/2306.06513v1
restoration. Instead of learning a single codebook for each image category, we learn a
https://arxiv.org/abs/2306.06513v1
restoration. Instead of learning a single codebook for each image category, we learn a