{"list":"other","total":75,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"2010.02502","title":"Denoising Diffusion Implicit Models","created":"2020-10-06","cited_by_count":9781},{"id":"2105.05233","title":"Diffusion Models Beat GANs on Image Synthesis","created":"2021-05-11","cited_by_count":8255},{"id":"1503.03585","title":"Deep Unsupervised Learning using Nonequilibrium Thermodynamics","created":"2015-03-12","cited_by_count":7058},{"id":"2205.11487","title":"Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding","created":"2022-05-23","cited_by_count":6355},{"id":"2102.12092","title":"Zero-Shot Text-to-Image Generation","created":"2021-02-24","cited_by_count":4288},{"id":"2012.09841","title":"Taming Transformers for High-Resolution Image Synthesis","created":"2020-12-17","cited_by_count":3253},{"id":"1606.03498","title":"Improved Techniques for Training GANs","created":"2016-06-10","cited_by_count":2970},{"id":"1602.07332","title":"Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations","created":"2016-02-23","cited_by_count":2656},{"id":"2104.08718","title":"CLIPScore: A Reference-free Evaluation Metric for Image Captioning","created":"2021-04-18","cited_by_count":2424},{"id":"2107.03006","title":"Structured Denoising Diffusion Models in Discrete State-Spaces","created":"2021-07-07","cited_by_count":1719},{"id":"1709.06158","title":"Matterport3D: Learning from RGB-D Data in Indoor Environments","created":"2017-09-18","cited_by_count":1376},{"id":"2112.03857","title":"Grounded Language-Image Pre-training","created":"2021-12-07","cited_by_count":1156},{"id":"1607.08822","title":"SPICE: Semantic Propositional Image Caption Evaluation","created":"2016-07-29","cited_by_count":824},{"id":"2111.14822","title":"Vector Quantized Diffusion Model for Text-to-Image Synthesis","created":"2021-11-29","cited_by_count":774},{"id":"2202.03052","title":"OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Framework","created":"2022-02-07","cited_by_count":745},{"id":"2401.12168","title":"SpatialVLM: Endowing Vision-Language Models with Spatial Reasoning Capabilities","created":"2024-01-22","cited_by_count":706},{"id":"2105.13290","title":"CogView: Mastering Text-to-Image Generation via Transformers","created":"2021-05-26","cited_by_count":694},{"id":"2309.05519","title":"NExT-GPT: Any-to-Any Multimodal LLM","created":"2023-09-11","cited_by_count":615},{"id":"2302.08113","title":"MultiDiffusion: Fusing Diffusion Paths for Controlled Image Generation","created":"2023-02-16","cited_by_count":536},{"id":"1701.02426","title":"Scene Graph Generation by Iterative Message Passing","created":"2017-01-10","cited_by_count":462},{"id":"1701.05517","title":"PixelCNN++: Improving the PixelCNN with Discretized Logistic Mixture Likelihood and Other Modifications","created":"2017-01-19","cited_by_count":417},{"id":"1711.06640","title":"Neural Motifs: Scene Graph Parsing with Global Context","created":"2017-11-17","cited_by_count":414},{"id":"2102.02779","title":"Unifying Vision-and-Language Tasks via Text Generation","created":"2021-02-04","cited_by_count":412},{"id":"1804.01622","title":"Image Generation from Scene Graphs","created":"2018-04-04","cited_by_count":324},{"id":"2205.00363","title":"Visual Spatial Reasoning","created":"2022-04-30","cited_by_count":293},{"id":"1910.02527","title":"3D Scene Graph: A Structure for Unified Semantics, 3D Space, and Camera","created":"2019-10-06","cited_by_count":281},{"id":"2207.07285","title":"X-CLIP: End-to-End Multi-grained Contrastive Learning for Video-Text Retrieval","created":"2022-07-15","cited_by_count":280},{"id":"2311.18651","title":"LL3DA: Visual Interactive Instruction Tuning for Omni-3D Understanding, Reasoning, and Planning","created":"2023-11-30","cited_by_count":210},{"id":"2004.03967","title":"Learning 3D Semantic Scene Graphs from 3D Indoor Reconstructions","created":"2020-04-08","cited_by_count":208},{"id":"2103.14898","title":"SceneGraphFusion: Incremental 3D Scene Graph Prediction from RGB-D Sequences","created":"2021-03-27","cited_by_count":163},{"id":"2501.03230","title":"Video-of-Thought: Step-by-Step Video Reasoning from Perception to Cognition","created":"2024-05-07","cited_by_count":153},{"id":"2101.06894","title":"Kimera: from SLAM to Spatial Perception with 3D Dynamic Scene Graphs","created":"2021-01-18","cited_by_count":144},{"id":"2406.19389","title":"OMG-LLaVA: Bridging Image-level, Object-level, Pixel-level Reasoning and Understanding","created":"2024-06-27","cited_by_count":127},{"id":"2402.11435","title":"Momentor: Advancing Video Large Language Model with Fine-Grained Temporal Reasoning","created":"2024-02-18","cited_by_count":122},{"id":"2308.05095","title":"LayoutLLM-T2I: Eliciting Layout Guidance from LLM for Text-to-Image Generation","created":"2023-08-09","cited_by_count":92},{"id":"2104.05832","title":"SpartQA: : A Textual Question Answering Benchmark for Spatial Reasoning","created":"2021-04-12","cited_by_count":77},{"id":"2208.13753","title":"Frido: Feature Pyramid Diffusion for Complex Scene Image Synthesis","created":"2022-08-29","cited_by_count":75},{"id":"1908.04929","title":"3-D Scene Graph: A Sparse and Semantic Representation of Physical Environments for Intelligent Agents","created":"2019-08-14","cited_by_count":74},{"id":"2004.02707","title":"Sub-Instruction Aware Vision-and-Language Navigation","created":"2020-04-06","cited_by_count":66},{"id":"2305.07154","title":"Foundations of Spatial Perception for Robotics: Hierarchical Representations and Real-time Systems","created":"2023-05-11","cited_by_count":60},{"id":"1907.09358","title":"Trends in Integration of Vision and Language Research: A Survey of Tasks, Datasets, and Methods","created":"2019-07-22","cited_by_count":55},{"id":"1908.02660","title":"SpatialSense: An Adversarially Crowdsourced Benchmark for Spatial Relation Recognition","created":"2019-08-07","cited_by_count":55},{"id":"2412.19806","title":"Vitron: A Unified Pixel-level Vision LLM for Understanding, Generating, Segmenting, Editing","created":"2024-10-08","cited_by_count":49},{"id":"2012.07061","title":"Improving Image Captioning by Leveraging Intra- and Inter-layer Global Representation in Transformer Network","created":"2020-12-13","cited_by_count":48},{"id":"1707.04879","title":"Listening while Speaking: Speech Chain by Deep Learning","created":"2017-07-16","cited_by_count":46},{"id":"2406.05127","title":"Towards Semantic Equivalence of Tokenization in Multimodal LLM","created":"2024-06-07","cited_by_count":45},{"id":"2307.15567","title":"Panoptic Scene Graph Generation with Semantics-Prototype Learning","created":"2023-07-28","cited_by_count":42},{"id":"2203.08075","title":"Things not Written in Text: Exploring Spatial Commonsense from Visual Signals","created":"2022-03-15","cited_by_count":41},{"id":"2112.01799","title":"Global Context with Discrete Diffusion in Vector Quantised Modelling for Image Generation","created":"2021-12-03","cited_by_count":40},{"id":"1706.02027","title":"Question Answering and Question Generation as Dual Tasks","created":"2017-06-07","cited_by_count":37},{"id":"2308.13812","title":"Dysen-VDM: Empowering Dynamics-aware Text-to-Video Diffusion with LLMs","created":"2023-08-26","cited_by_count":35},{"id":"2309.06635","title":"Collaborative Dynamic 3D Scene Graphs for Automated Driving","created":"2023-09-12","cited_by_count":34},{"id":"1707.00415","title":"Dual Supervised Learning","created":"2017-07-03","cited_by_count":33},{"id":"2407.21534","title":"ControlMLLM: Training-Free Visual Prompt Learning for Multimodal Large Language Models","created":"2024-07-31","cited_by_count":33},{"id":"2406.19255","title":"Enhancing Video-Language Representations with Structural Spatio-Temporal Alignment","created":"2024-06-27","cited_by_count":32},{"id":"2106.13948","title":"Core Challenges in Embodied Vision-Language Planning","created":"2021-06-26","cited_by_count":30},{"id":"2305.12256","title":"Scene Graph as Pivoting: Inference-time Image-free Unsupervised Multimodal Machine Translation with Visual Scene Hallucination","created":"2023-05-20","cited_by_count":27},{"id":"2111.00312","title":"3DP3: 3D Scene Perception via Probabilistic Programming","created":"2021-10-30","cited_by_count":26},{"id":"2312.11713","title":"Indoor and Outdoor 3D Scene Graph Generation via Language-Enabled Spatial Ontologies","created":"2023-12-18","cited_by_count":25},{"id":"1906.00717","title":"Masked Non-Autoregressive Image Captioning","created":"2019-06-03","cited_by_count":22},{"id":"1912.06365","title":"Fast Image Caption Generation with Position Alignment","created":"2019-12-13","cited_by_count":21},{"id":"2308.09778","title":"Towards Grounded Visual Spatial Reasoning in Multi-Modal Vision Language Models","created":"2023-08-18","cited_by_count":18},{"id":"2211.11694","title":"Exploring Discrete Diffusion Models for Image Captioning","created":"2022-11-21","cited_by_count":16},{"id":"2305.11768","title":"Generating Visual Spatial Description via Holistic 3D Scene Understanding","created":"2023-05-19","cited_by_count":16},{"id":"2305.12260","title":"Cross2StrA: Unpaired Cross-lingual Image Captioning with Cross-lingual Cross-modal Structure-pivoted Alignment","created":"2023-05-20","cited_by_count":15},{"id":"2308.05081","title":"Constructing Holistic Spatio-Temporal Scene Graph for Video Semantic Role Labeling","created":"2023-08-09","cited_by_count":15},{"id":"1905.06196","title":"Dual Supervised Learning for Natural Language Understanding and Generation","created":"2019-05-15","cited_by_count":14},{"id":"2306.07735","title":"Discrete Graph Auto-Encoder","created":"2023-06-13","cited_by_count":10},{"id":"2310.05867","title":"Domain-wise Invariant Learning for Panoptic Scene Graph Generation","created":"2023-10-09","cited_by_count":7},{"id":"1906.00575","title":"Jointly Learning Semantic Parser and Natural Language Generator via Dual Information Maximization","created":"2019-06-03","cited_by_count":6},{"id":"2210.11109","title":"Visual Spatial Description: Controlled Spatial-Oriented Image-to-Text Generation","created":"2022-10-20","cited_by_count":6},{"id":"2305.12144","title":"DiffCap: Exploring Continuous Diffusion on Image Captioning","created":"2023-05-20","cited_by_count":5}],"next_cursor":null}