{"list":"other","total":52,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2301.12597","title":"BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models","created":"2023-01-30","cited_by_count":6137},{"id":"2502.13923","title":"Qwen2.5-VL Technical Report","created":"2025-02-19","cited_by_count":5587},{"id":"2104.09864","title":"RoFormer: Enhanced Transformer with Rotary Position Embedding","created":"2021-04-20","cited_by_count":4703},{"id":"2408.00714","title":"SAM 2: Segment Anything in Images and Videos","created":"2024-08-01","cited_by_count":2863},{"id":"1602.07332","title":"Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations","created":"2016-02-23","cited_by_count":2656},{"id":"2403.04652","title":"Yi: Open Foundation Models by 01.AI","created":"2024-03-07","cited_by_count":719},{"id":"2003.00982","title":"Benchmarking Graph Neural Networks","created":"2020-03-02","cited_by_count":680},{"id":"2412.13663","title":"Smarter, Better, Faster, Longer: A Modern Bidirectional Encoder for Fast, Memory Efficient, and Long Context Finetuning and Inference","created":"2024-12-18","cited_by_count":554},{"id":"2009.03509","title":"Masked Label Prediction: Unified Message Passing Model for Semi-Supervised Classification","created":"2020-09-08","cited_by_count":506},{"id":"2401.17270","title":"YOLO-World: Real-Time Open-Vocabulary Object Detection","created":"2024-01-30","cited_by_count":503},{"id":"2309.16650","title":"ConceptGraphs: Open-Vocabulary 3D Scene Graphs for Perception and Planning","created":"2023-09-28","cited_by_count":365},{"id":"1912.06992","title":"Action Genome: Actions as Composition of Spatio-temporal Scene Graphs","created":"2019-12-15","cited_by_count":250},{"id":"2402.07630","title":"G-Retriever: Retrieval-Augmented Generation for Textual Graph Understanding and Question Answering","created":"2024-02-12","cited_by_count":223},{"id":"2405.09711","title":"STAR: A Benchmark for Situated Reasoning in Real-World Videos","created":"2024-05-15","cited_by_count":213},{"id":"2412.04468","title":"NVILA: Efficient Frontier Visual Language Models","created":"2024-12-05","cited_by_count":209},{"id":"2305.06988","title":"Self-Chained Image-Language Model for Video Localization and Question Answering","created":"2023-05-11","cited_by_count":203},{"id":"2403.17846","title":"Hierarchical Open-Vocabulary 3D Scene Graphs for Language-Grounded Robot Navigation","created":"2024-03-26","cited_by_count":196},{"id":"2302.11636","title":"Do We Really Need Complicated Model Architectures For Temporal Networks?","created":"2023-02-22","cited_by_count":143},{"id":"2103.16002","title":"AGQA: A Benchmark for Compositional Spatio-Temporal Reasoning","created":"2021-03-30","cited_by_count":120},{"id":"2402.05862","title":"Let Your Graph Do the Talking: Encoding Structured Data for LLMs","created":"2024-02-08","cited_by_count":118},{"id":"2207.11247","title":"Panoptic Scene Graph Generation","created":"2022-07-22","cited_by_count":114},{"id":"2201.11460","title":"RelTR: Relation Transformer for Scene Graph Generation","created":"2022-01-27","cited_by_count":96},{"id":"2404.13696","title":"Clio: Real-time Task-Driven Open-Set 3D Scene Graphs","created":"2024-04-21","cited_by_count":81},{"id":"2212.09522","title":"MIST: Multi-modal Iterative Spatial-Temporal Transformer for Long-form Video Question Answering","created":"2022-12-19","cited_by_count":55},{"id":"2312.03391","title":"Action Scene Graphs for Long-Form Understanding of Egocentric Videos","created":"2023-12-06","cited_by_count":51},{"id":"2305.17497","title":"FACTUAL: A Benchmark for Faithful and Consistent Textual Scene Graph Parsing","created":"2023-05-27","cited_by_count":50},{"id":"2404.02072","title":"EGTR: Extracting Graph from Transformer for Scene Graph Generation","created":"2024-04-02","cited_by_count":47},{"id":"2311.17058","title":"Panoptic Video Scene Graph Generation","created":"2023-11-28","cited_by_count":46},{"id":"2501.02765","title":"Visual Large Language Models for Generalized and Specialized Applications","created":"2025-01-06","cited_by_count":36},{"id":"2409.18431","title":"Search3D: Hierarchical Open-Vocabulary 3D Segmentation","created":"2024-09-27","cited_by_count":31},{"id":"2202.09277","title":"(2.5+1)D Spatio-Temporal Scene Graphs for Video Question Answering","created":"2022-02-18","cited_by_count":30},{"id":"2310.10404","title":"LLM4SGG: Large Language Models for Weakly Supervised Scene Graph Generation","created":"2023-10-16","cited_by_count":30},{"id":"2409.18938","title":"From Seconds to Hours: Reviewing MultiModal Large Language Models on Comprehensive Long Video Understanding","created":"2024-09-27","cited_by_count":30},{"id":"2312.08367","title":"ViLA: Efficient Video-Language Alignment for Video Question Answering","created":"2023-12-13","cited_by_count":23},{"id":"2405.16925","title":"OED: Towards One-stage End-to-End Dynamic Scene Graph Generation","created":"2024-05-27","cited_by_count":23},{"id":"2405.10305","title":"4D Panoptic Scene Graph Generation","created":"2024-05-16","cited_by_count":22},{"id":"2412.00161","title":"STEP: Enhancing Video-LLMs' Compositional Reasoning by Spatio-Temporal Graph-guided Self-Training","created":"2024-11-29","cited_by_count":22},{"id":"2412.07012","title":"ProVision: Programmatically Scaling Vision-centric Instruction Data for Multimodal Language Models","created":"2024-12-09","cited_by_count":21},{"id":"2407.15047","title":"End-to-End Video Question Answering with Frame Scoring Mechanisms and Adaptive Sampling","created":"2024-07-21","cited_by_count":19},{"id":"2411.18042","title":"HyperGLM: HyperGraph for Video Scene Graph Generation and Anticipation","created":"2024-11-27","cited_by_count":19},{"id":"2306.17778","title":"Look, Remember and Reason: Grounded reasoning in videos with language models","created":"2023-06-30","cited_by_count":14},{"id":"2402.16050","title":"Efficient Temporal Extrapolation of Multimodal Large Language Models with Temporal Grounding Bridge","created":"2024-02-25","cited_by_count":14},{"id":"2204.06105","title":"AGQA 2.0: An Updated Benchmark for Compositional Spatio-Temporal Reasoning","created":"2022-04-12","cited_by_count":10},{"id":"2402.10698","title":"Question-Instructed Visual Descriptions for Zero-Shot Video Question Answering","created":"2024-02-16","cited_by_count":9},{"id":"2401.01529","title":"Glance and Focus: Memory Prompting for Multi-Event Video Question Answering","created":"2024-01-03","cited_by_count":8},{"id":"2407.06723","title":"Graph-Based Captioning: Enhancing Visual Descriptions by Interconnecting Region Captions","created":"2024-07-09","cited_by_count":7},{"id":"2411.13754","title":"Learning to Reason Iteratively and Parallelly for Complex Visual Reasoning Scenarios","created":"2024-11-20","cited_by_count":3},{"id":"2210.03941","title":"Learning Fine-Grained Visual Understanding for Video Question Answering via Decoupling Spatial-Temporal Modeling","created":"2022-10-08","cited_by_count":2}],"next_cursor":null}