{"list":"other","total":57,"rows":[{"id":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"id":"2212.09748","title":"Scalable Diffusion Models with Transformers","created":"2022-12-19","cited_by_count":6054},{"id":"2210.02747","title":"Flow Matching for Generative Modeling","created":"2022-10-06","cited_by_count":5702},{"id":"1711.00937","title":"Neural Discrete Representation Learning","created":"2017-11-02","cited_by_count":4712},{"id":"2102.12092","title":"Zero-Shot Text-to-Image Generation","created":"2021-02-24","cited_by_count":4288},{"id":"2206.00364","title":"Elucidating the Design Space of Diffusion-Based Generative Models","created":"2022-06-01","cited_by_count":3045},{"id":"1602.07332","title":"Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations","created":"2016-02-23","cited_by_count":2656},{"id":"2112.01527","title":"Masked-attention Mask Transformer for Universal Image Segmentation","created":"2021-12-02","cited_by_count":2351},{"id":"1709.07871","title":"FiLM: Visual Reasoning with a General Conditioning Layer","created":"2017-09-22","cited_by_count":2333},{"id":"1612.03975","title":"ConceptNet 5.5: An Open Multilingual Graph of General Knowledge","created":"2016-12-12","cited_by_count":1067},{"id":"2104.13921","title":"Open-vocabulary Object Detection via Vision and Language Knowledge Distillation","created":"2021-04-28","cited_by_count":906},{"id":"2401.12168","title":"SpatialVLM: Endowing Vision-Language Models with Spatial Reasoning Capabilities","created":"2024-01-22","cited_by_count":706},{"id":"2209.14734","title":"DiGress: Discrete Denoising diffusion for graph generation","created":"2022-09-29","cited_by_count":520},{"id":"2004.05718","title":"Principal Neighbourhood Aggregation for Graph Nets","created":"2020-04-12","cited_by_count":478},{"id":"1701.02426","title":"Scene Graph Generation by Iterative Message Passing","created":"2017-01-10","cited_by_count":462},{"id":"1711.06640","title":"Neural Motifs: Scene Graph Parsing with Global Context","created":"2017-11-17","cited_by_count":414},{"id":"2303.04803","title":"Open-Vocabulary Panoptic Segmentation with Text-to-Image Diffusion Models","created":"2023-03-08","cited_by_count":375},{"id":"2407.15595","title":"Discrete Flow Matching","created":"2024-07-22","cited_by_count":317},{"id":"2402.04997","title":"Generative Flows on Discrete State-Spaces: Enabling Multimodal Flows with Applications to Protein Co-Design","created":"2024-02-07","cited_by_count":305},{"id":"1812.01880","title":"Learning to Compose Dynamic Tree Structures for Visual Contexts","created":"2018-12-05","cited_by_count":259},{"id":"1505.04474","title":"Visual Semantic Role Labeling","created":"2015-05-17","cited_by_count":190},{"id":"2003.12962","title":"GPS-Net: Graph Property Sensing Network for Scene Graph Generation","created":"2020-03-29","cited_by_count":166},{"id":"1609.02200","title":"Discrete Variational Autoencoders","created":"2016-09-07","cited_by_count":125},{"id":"2402.04717","title":"InstructScene: Instruction-Driven 3D Indoor Scene Synthesis with Semantic Graph Prior","created":"2024-02-07","cited_by_count":117},{"id":"2207.11247","title":"Panoptic Scene Graph Generation","created":"2022-07-22","cited_by_count":114},{"id":"2112.12970","title":"SGTR: End-to-end Scene Graph Generation with Transformer","created":"2021-12-24","cited_by_count":103},{"id":"2204.01613","title":"SPECTRE: Spectral Conditioning Helps to Overcome the Expressivity Limits of One-shot Graph Generators","created":"2022-04-04","cited_by_count":99},{"id":"2201.11460","title":"RelTR: Relation Transformer for Scene Graph Generation","created":"2022-01-27","cited_by_count":96},{"id":"2307.08849","title":"Autoregressive Diffusion Model for Graph Generation","created":"2023-07-17","cited_by_count":83},{"id":"2406.04843","title":"Variational Flow Matching for Graph Generation","created":"2024-06-07","cited_by_count":83},{"id":"2410.04263","title":"DeFoG: Discrete Flow Matching for Graph Generation","created":"2024-10-05","cited_by_count":82},{"id":"2405.11416","title":"Discrete-state Continuous-time Diffusion for Graph Generation","created":"2024-05-19","cited_by_count":76},{"id":"2208.08165","title":"Towards Open-vocabulary Scene Graph Generation with Prompt-based Finetuning","created":"2022-08-17","cited_by_count":54},{"id":"2404.02072","title":"EGTR: Extracting Graph from Transformer for Scene Graph Generation","created":"2024-04-02","cited_by_count":47},{"id":"2311.08403","title":"Instant3D: Instant Text-to-3D Generation","created":"2023-11-14","cited_by_count":45},{"id":"2404.00906","title":"From Pixels to Graphs: Open-Vocabulary Scene Graph Generation with Vision-Language Models","created":"2024-04-01","cited_by_count":43},{"id":"2410.22388","title":"ET-Flow: Equivariant Flow-Matching for Molecular Conformer Generation","created":"2024-10-29","cited_by_count":43},{"id":"2307.15567","title":"Panoptic Scene Graph Generation with Semantics-Prototype Learning","created":"2023-07-28","cited_by_count":42},{"id":"2303.07096","title":"Prototype-based Embedding Network for Scene Graph Generation","created":"2023-03-13","cited_by_count":37},{"id":"2301.03046","title":"STPrivacy: Spatio-Temporal Privacy-Preserving Action Recognition","created":"2023-01-08","cited_by_count":29},{"id":"2311.10988","title":"Expanding Scene Graph Boundaries: Fully Open-vocabulary Scene Graph Generation via Visual-Concept Alignment and Retention","created":"2023-11-18","cited_by_count":29},{"id":"2406.07221","title":"Open-World Human-Object Interaction Detection via Multi-modal Prompts","created":"2024-06-11","cited_by_count":28},{"id":"2412.00832","title":"EventGPT: Event Stream Understanding with Multimodal Large Language Models","created":"2024-12-01","cited_by_count":28},{"id":"2006.07585","title":"Learning from the Scene and Borrowing from the Rich: Tackling the Long Tail in Scene Graph Generation","created":"2020-06-13","cited_by_count":22},{"id":"2108.05884","title":"Unconditional Scene Graph Generation","created":"2021-08-12","cited_by_count":22},{"id":"2503.20211","title":"Synthetic-to-Real Self-supervised Robust Depth Estimation via Learning with Motion and Structure Priors","created":"2025-03-26","cited_by_count":22},{"id":"2307.08699","title":"Pair then Relation: Pair-Net for Panoptic Scene Graph Generation","created":"2023-07-17","cited_by_count":17},{"id":"2505.19694","title":"Knowledge-Aligned Counterfactual-Enhancement Diffusion Perception for Unsupervised Cross-Domain Visual Emotion Recognition","created":"2025-05-26","cited_by_count":17},{"id":"2407.11213","title":"OpenPSG: Open-set Panoptic Scene Graph Generation via Large Multimodal Models","created":"2024-07-15","cited_by_count":16},{"id":"2403.14886","title":"DSGG: Dense Relation Transformer for an End-to-end Scene Graph Generation","created":"2024-03-21","cited_by_count":11},{"id":"2403.17709","title":"Groupwise Query Specialization and Quality-Aware Multi-Assignment for Transformer-based Visual Relationship Detection","created":"2024-03-26","cited_by_count":11},{"id":"2503.15005","title":"Universal Scene Graph Generation","created":"2025-03-19","cited_by_count":11},{"id":"2602.24144","title":"Fixed Anchors Are Not Enough: Dynamic Retrieval and Persistent Homology for Dataset Distillation","created":"2026-02-27","cited_by_count":11},{"id":"2409.10262","title":"Hydra-SGG: Hybrid Relation Assignment for One-stage Scene Graph Generation","created":"2024-09-16","cited_by_count":10},{"id":"1707.02112","title":"Deep Discrete Hashing with Self-supervised Pairwise Labels","created":"2017-07-07","cited_by_count":8},{"id":"2303.04634","title":"Transformer-based Image Generation from Scene Graphs","created":"2023-03-08","cited_by_count":8},{"id":"2511.15085","title":"TiCAL:Typicality-Based Consistency-Aware Learning for Multimodal Emotion Recognition","created":"2025-11-19","cited_by_count":5}],"next_cursor":null}