On the public citation graph

Teaching Compositionality to CNNs

0 signed · 95 inferred · view as graph

Inferred edges come from two machine sources: sweeps of open repository metadata (mostly SSRN and Zenodo), and a bulk OpenAlex citation snapshot. Every row below is labelled with the one it came from. Neither is a complete citation index — absence here is not evidence of absence.

Is this your work? Sign in with ORCID and put your name on the claims that are yours.
Claim with ORCID
Reference health. See whether every reference in this work resolves to a known work and none has been retracted — and get a dated CiteStamped badge you can embed.
See reference health

What this work says

Outgoing claims: the papers this work cites, builds on, or argues with.

inferredcites →https://doi.org/10.1007/978-3-319-10602-1_48openalex-snapshot
Microsoft COCO: Common Objects in Context
inferredcites →https://doi.org/10.1007/978-3-319-46475-6_1openalex-snapshot
The Curious Robot: Learning Visual Representations via Physical Interactions
inferredcites →https://doi.org/10.1007/978-3-319-54193-8_16openalex-snapshot
Object-Centric Representation Learning from Unlabeled Videos
inferredcites →https://doi.org/10.1007/978-3-642-33783-3_4openalex-snapshot
Contextual Object Detection Using Set-Based Classification
inferredcites →https://doi.org/10.1016/j.cviu.2010.02.004openalex-snapshot
Context based object categorization: A critical survey
inferredcites →https://doi.org/10.1016/j.neunet.2014.09.003openalex-snapshot
Deep learning in neural networks: An overview
inferredcites →https://doi.org/10.1016/j.patrec.2011.12.004openalex-snapshot
Context models and out-of-context objects
inferredcites →https://doi.org/10.1016/j.tics.2007.09.009openalex-snapshot
The role of context in object recognition
inferredcites →https://doi.org/10.1038/29537openalex-snapshot
Cortical feedback improves discrimination between figure and background by V1, V2 and V3 neurons
inferredcites →https://doi.org/10.1093/cercor/bhw235openalex-snapshot
Texture Segregation Causes Early Figure Enhancement and Later Ground Suppression in Areas V1 and V4 of Visual Cortex
inferredcites →https://doi.org/10.1109/5.726791openalex-snapshot
Gradient-based learning applied to document recognition
inferredcites →https://doi.org/10.1109/cvpr.2007.383269openalex-snapshot
Towards Scalable Representations of Object Categories: Learning a Hierarchy of Parts
inferredcites →https://doi.org/10.1109/cvpr.2009.5206532openalex-snapshot
An empirical study of context in object detection
inferredcites →https://doi.org/10.1109/cvpr.2010.5540096openalex-snapshot
Latent hierarchical structural learning for object detection
inferredcites →https://doi.org/10.1109/cvpr.2011.5995357openalex-snapshot
Shared parts for deformable part-based models
inferredcites →https://doi.org/10.1109/cvpr.2011.5995711openalex-snapshot
Recognition using visual phrases
inferredcites →https://doi.org/10.1109/cvpr.2013.422openalex-snapshot
Occlusion Patterns for Object Class Detection
inferredcites →https://doi.org/10.1109/cvpr.2015.7298594openalex-snapshot
Going deeper with convolutions
inferredcites →https://doi.org/10.1109/cvpr.2015.7298642openalex-snapshot
Hypercolumns for object segmentation and fine-grained localization
inferredcites →https://doi.org/10.1109/cvpr.2015.7298668openalex-snapshot
Is object localization for free? - Weakly-supervised learning with convolutional neural networks
inferredcites →https://doi.org/10.1109/cvpr.2015.7298788openalex-snapshot
Semantic part segmentation using compositional model combining shape and appearance
inferredcites →https://doi.org/10.1109/cvpr.2015.7298932openalex-snapshot
Deep visual-semantic alignments for generating image descriptions
inferredcites →https://doi.org/10.1109/cvpr.2015.7298935openalex-snapshot
Show and tell: A neural image caption generator
inferredcites →https://doi.org/10.1109/cvpr.2016.418openalex-snapshot
Slow and Steady Feature Analysis: Higher Order Temporal Coherence in Video
inferredcites →https://doi.org/10.1109/cvpr.2016.96openalex-snapshot
Learning with Side Information through Modality Hallucination
inferredcites →https://doi.org/10.1109/iccv.2015.13openalex-snapshot
Learning to See by Moving
inferredcites →https://doi.org/10.1109/icpr.2016.7900171openalex-snapshot
Towards deep compositional networks
inferredcites →https://doi.org/10.1109/tpami.2009.22openalex-snapshot
Learning the Compositional Nature of Visual Object Categories for Recognition
inferredcites →https://doi.org/10.1109/tpami.2012.269openalex-snapshot
Learning with Hierarchical-Deep Models
inferredcites →https://doi.org/10.1109/tpami.2013.35openalex-snapshot
Learning AND-OR Templates for Object Recognition and Detection
inferredcites →https://doi.org/10.1109/tpami.2015.2497699openalex-snapshot
Learning And-Or Model to Represent Context and Occlusion for Car Detection and Viewpoint Estimation
inferredcites →https://doi.org/10.1113/jphysiol.1962.sp006837openalex-snapshot
Receptive fields, binocular interaction and functional architecture in the cat's visual cortex
inferredcites →https://doi.org/10.1162/neco.1989.1.4.541openalex-snapshot
Backpropagation Applied to Handwritten Zip Code Recognition
inferredcites →https://doi.org/10.4230/oasics.dx.2026.15openalex-snapshot
AutoResearch Lite: a reproducible paper-inspired experiment runner (Adam mechanism reproduction and convergence-speed comparison)
inferredcites →https://doi.org/10.48550/arxiv.1407.1808openalex-snapshot
Simultaneous Detection and Segmentation
inferredcites →https://doi.org/10.48550/arxiv.1409.4842openalex-snapshot
Going Deeper with Convolutions
inferredcites →https://doi.org/10.48550/arxiv.1411.4555openalex-snapshot
Show and Tell: A Neural Image Caption Generator
inferredcites →https://doi.org/10.48550/arxiv.1412.6806openalex-snapshot
Striving for Simplicity: The All Convolutional Net
inferredcites →https://doi.org/10.48550/arxiv.1505.01596openalex-snapshot
Learning to See by Moving
inferredcites →https://doi.org/10.48550/arxiv.1511.08177openalex-snapshot
Exploring Person Context and Local Scene Context for Object Detection
inferredcites →https://doi.org/10.48550/arxiv.1603.08575openalex-snapshot
Attend, Infer, Repeat: Fast Scene Understanding with Generative Models
inferredcites →https://doi.org/10.48550/arxiv.1609.03795openalex-snapshot
Towards Deep Compositional Networks

What points at this work

Incoming claims: where this work appears in other papers’ reference lists and arguments.

inferred← citeshttps://doi.org/10.1007/978-3-030-44584-3_40openalex-snapshot
Interpretable Neuron Structuring with Graph Spectral Regularization
inferred← citeshttps://doi.org/10.1007/978-3-031-72744-3_5openalex-snapshot
Enhancing Cross-Modal Medical Image Segmentation Through Compositionality
inferred← citeshttps://doi.org/10.1007/978-981-99-3966-4_8openalex-snapshot
Computer Vision Technology: Do Deep Neural Networks Model Nonlinear Compositionality in the Brain’s Representation of Human–Object Interactions?
inferred← citeshttps://doi.org/10.1007/s11263-020-01401-3openalex-snapshot
Compositional Convolutional Neural Networks: A Robust and Interpretable Model for Object Recognition Under Occlusion
inferred← citeshttps://doi.org/10.1007/s13748-022-00290-6openalex-snapshot
Robust appearance modeling for object detection and tracking: a survey of deep learning approaches
inferred← citeshttps://doi.org/10.1016/j.adhoc.2020.102346openalex-snapshot
Explaining the Behavior of Neuron Activations in Deep Neural Networks
inferred← citeshttps://doi.org/10.1016/j.eswa.2021.115127openalex-snapshot
Deep graph convolutional reinforcement learning for financial portfolio management – DeepPocket
inferred← citeshttps://doi.org/10.1016/j.inffus.2021.09.022openalex-snapshot
EXplainable Neural-Symbolic Learning (X-NeSyL) methodology to fuse deep learning representations with expert knowledge graphs: The MonuMAI cultural heritage use case
inferred← citeshttps://doi.org/10.1016/j.isci.2021.103581openalex-snapshot
CX-ToM: Counterfactual explanations with theory-of-mind for enhancing human trust in image recognition models
inferred← citeshttps://doi.org/10.1016/j.jvcir.2022.103682openalex-snapshot
Learn decision trees with deep visual primitives
inferred← citeshttps://doi.org/10.1016/j.media.2022.102516openalex-snapshot
Learning disentangled representations in the imaging domain
inferred← citeshttps://doi.org/10.1016/j.media.2025.103529openalex-snapshot
AI-based association analysis for medical imaging using latent-space geometric confounder correction
inferred← citeshttps://doi.org/10.1038/s41598-024-70695-xopenalex-snapshot
Enhancing YOLO for occluded vehicle detection with grouped orthogonal attention and dense object repulsion
inferred← citeshttps://doi.org/10.1109/ciss50987.2021.9400221openalex-snapshot
Compositional Generative Networks and Robustness to Perceptible Image Changes
inferred← citeshttps://doi.org/10.1109/crv55824.2022.00026openalex-snapshot
Occluded Text Detection and Recognition in the Wild
inferred← citeshttps://doi.org/10.1109/cvpr.2018.00920openalex-snapshot
Interpretable Convolutional Neural Networks
inferred← citeshttps://doi.org/10.1109/cvpr42600.2020.00869openalex-snapshot
Interpretable and Accurate Fine-grained Recognition via Region Grouping
inferred← citeshttps://doi.org/10.1109/cvpr42600.2020.00896openalex-snapshot
Compositional Convolutional Neural Networks: A Deep Architecture With Innate Robustness to Partial Occlusion
inferred← citeshttps://doi.org/10.1109/cvpr46437.2021.00530openalex-snapshot
Learning Compositional Representation for 4D Captures with Neural ODE
inferred← citeshttps://doi.org/10.1109/cvpr46437.2021.01113openalex-snapshot
AGQA: A Benchmark for Compositional Spatio-Temporal Reasoning
inferred← citeshttps://doi.org/10.1109/icassp49357.2023.10096573openalex-snapshot
Multi-Scale Compositional Constraints for Representation Learning on Videos
inferred← citeshttps://doi.org/10.1109/iccv.2019.00647openalex-snapshot
Learning Compositional Representations for Few-Shot Recognition
inferred← citeshttps://doi.org/10.1109/iccv.2019.00928openalex-snapshot
Explaining Neural Networks Semantically and Quantitatively
inferred← citeshttps://doi.org/10.1109/iccvw.2019.00518openalex-snapshot
Semantically Interpretable Activation Maps: what-where-how explanations within CNNs
inferred← citeshttps://doi.org/10.1109/iccvw69036.2025.00079openalex-snapshot
Do VLMs Have Bad Eyes? Diagnosing Compositional Failures via Mechanistic Interpretability
inferred← citeshttps://doi.org/10.1109/ijcnn52387.2021.9533955openalex-snapshot
Designing a Partially Understandable Neural Network through Semantic Embedding
inferred← citeshttps://doi.org/10.1109/tmi.2024.3358955openalex-snapshot
Compositionally Equivariant Representation Learning
inferred← citeshttps://doi.org/10.1109/tpami.2019.2955476openalex-snapshot
Text-Guided Neural Network Training for Image Recognition in Natural Scenes and Medicine
inferred← citeshttps://doi.org/10.1109/trpms.2021.3066428openalex-snapshot
On Interpretability of Artificial Neural Networks: A Survey
inferred← citeshttps://doi.org/10.1109/wacv45572.2020.9093560openalex-snapshot
Combining Compositional Models and Deep Networks For Robust Object Classification under Occlusion
inferred← citeshttps://doi.org/10.1109/wacv48630.2021.00034openalex-snapshot
Compositional Embeddings for Multi-Label One-Shot Learning
inferred← citeshttps://doi.org/10.1109/wcsp49889.2020.9299736openalex-snapshot
Heterogeneous Edge CNN Hardware Accelerator
inferred← citeshttps://doi.org/10.1111/ejn.15746openalex-snapshot
Using compositionality to understand parts in whole objects
inferred← citeshttps://doi.org/10.1145/3474557openalex-snapshot
Semantic Explanation for Deep Neural Networks Using Feature Interactions
inferred← citeshttps://doi.org/10.1152/jn.00160.2021openalex-snapshot
A separable neural code in monkey IT enables perfect CAPTCHA decoding
inferred← citeshttps://doi.org/10.1371/journal.pone.0270904openalex-snapshot
A survey on text classification: Practical perspectives on the Italian language
inferred← citeshttps://doi.org/10.18653/v1/2020.repl4nlp-1openalex-snapshot
Proceedings of the 5th Workshop on Representation Learning for NLP
inferred← citeshttps://doi.org/10.18653/v1/2020.repl4nlp-1.22openalex-snapshot
Evaluating Compositionality of Sentence Representation Models
inferred← citeshttps://doi.org/10.24963/ijcai.2021/409openalex-snapshot
Interpretable Compositional Convolutional Neural Networks
inferred← citeshttps://doi.org/10.32470/ccn.2019.1269-0openalex-snapshot
Do Deep Neural Networks Model Nonlinear Compositionality in the Neural Representation of Human-Object Interactions?
inferred← citeshttps://doi.org/10.3389/frai.2021.642263openalex-snapshot
Rule Extraction From Binary Neural Networks With Convolutional Rules for Model Validation
inferred← citeshttps://doi.org/10.3389/frai.2022.806403openalex-snapshot
A Model of Unified Perception and Cognition
inferred← citeshttps://doi.org/10.3390/info13020083openalex-snapshot
A Survey on Text Classification Algorithms: From Text to Predictions
inferred← citeshttps://doi.org/10.48550/arxiv.1805.07468openalex-snapshot
Unsupervised Learning of Neural Networks to Explain Neural Networks
inferred← citeshttps://doi.org/10.48550/arxiv.1901.02184openalex-snapshot
Explaining AlphaGo: Interpreting Contextual Effects in Neural Networks
inferred← citeshttps://doi.org/10.48550/arxiv.1905.04598openalex-snapshot
Robustness of Object Recognition under Extreme Occlusion in Humans and Computational Models
inferred← citeshttps://doi.org/10.48550/arxiv.1906.04833openalex-snapshot
Weakly-supervised Compositional FeatureAggregation for Few-shot Recognition
inferred← citeshttps://doi.org/10.48550/arxiv.1911.09017openalex-snapshot
Towards a Unified Evaluation of Explanation Methods without Ground Truth
inferred← citeshttps://doi.org/10.48550/arxiv.1912.12179openalex-snapshot
Locality and compositionality in zero-shot learning
inferred← citeshttps://doi.org/10.48550/arxiv.2010.13320openalex-snapshot
Zero-Shot Learning from scratch (ZFS): leveraging local compositional representations
inferred← citeshttps://doi.org/10.70675/1c35c522z32c3z4c0aza5eaz331e61ba1cd3openalex-snapshot
Une Approche Collaborative pour la Classification des Sites Web
inferred← citeshttps://doi.org/10.70675/2b59f598z2028z49afz8a20z29b21f19f394openalex-snapshot
A Neural-Symbolic learning framework to produce interpretable predictions for image classification
inferred← citeshttps://doi.org/10.70675/d7175e36z7156z47c3za09bz49b02a753fd7openalex-snapshot
Deep learning for action recognition in videos
Editorial review for independent work. ICSAC — the Institute for Complexity Science and Advanced Computing — runs a structured editorial panel for researchers publishing outside journals, and publishes on CiteStamp rails. Submission is free and goes through ORCID: icsacinstitute.org/submit.