{"total":58,"rows":[{"id":"2303.06349","title":"Resurrecting Recurrent Neural Networks for Long Sequences","created":"2023-03-11","cited_by_count":408,"area":null},{"id":"2312.17235","title":"A Simple LLM Framework for Long-Range Video Question-Answering","created":"2023-12-28","cited_by_count":178,"area":null},{"id":"2301.02311","title":"HierVL: Learning Hierarchical Video-Language Embeddings","created":"2023-01-05","cited_by_count":66,"area":null},{"id":"2406.12846","title":"DrVideo: Document Retrieval Based Long Video Understanding","created":"2024-06-18","cited_by_count":65,"area":null},{"id":"2302.06646","title":"Simple Hardware-Efficient Long Convolutions for Sequence Modeling","created":"2023-02-13","cited_by_count":62,"area":null},{"id":"2404.09516","title":"State Space Model for New-Generation Network Alternative to Transformers: A Survey","created":"2024-04-15","cited_by_count":59,"area":null},{"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,"area":null},{"id":"2212.14427","title":"Efficient Movie Scene Detection using State-Space Transformers","created":"2022-12-29","cited_by_count":51,"area":null},{"id":"2312.14556","title":"CaptainCook4D: A Dataset for Understanding Errors in Procedural Activities","created":"2023-12-22","cited_by_count":51,"area":null},{"id":"2210.02396","title":"Temporally Consistent Transformers for Video Generation","created":"2022-10-05","cited_by_count":44,"area":null},{"id":"2210.06583","title":"S4ND: Modeling Images and Videos as Multidimensional Signals Using State Spaces","created":"2022-10-12","cited_by_count":41,"area":null},{"id":"2312.07395","title":"A Simple Recipe for Contrastively Pre-training Video-First Encoders Beyond 16 Frames","created":"2023-12-12","cited_by_count":34,"area":null},{"id":"2502.06020","title":"Temporal Working Memory: Query-Guided Segment Refinement for Enhanced Multimodal Understanding","created":"2025-02-09","cited_by_count":28,"area":null},{"id":"2209.10918","title":"CONE: An Efficient COarse-to-fiNE Alignment Framework for Long Video Temporal Grounding","created":"2022-09-22","cited_by_count":27,"area":null},{"id":"2503.09590","title":"BIMBA: Selective-Scan Compression for Long-Range Video Question Answering","created":"2025-03-12","cited_by_count":24,"area":null},{"id":"2408.09178","title":"MambaTrack: A Simple Baseline for Multiple Object Tracking with State Space Model","created":"2024-08-17","cited_by_count":18,"area":null},{"id":"2503.20781","title":"BASKET: A Large-Scale Video Dataset for Fine-Grained Skill Estimation","created":"2025-03-26","cited_by_count":17,"area":null},{"id":"2407.21757","title":"Learning Video Context as Interleaved Multimodal Sequences","created":"2024-07-31","cited_by_count":16,"area":null},{"id":"2404.00272","title":"HSIMamba: Hyperpsectral Imaging Efficient Feature Learning with Bidirectional State Space for Classification","created":"2024-03-30","cited_by_count":14,"area":null},{"id":"2409.06299","title":"Enhancing Long Video Understanding via Hierarchical Event-Based Memory","created":"2024-09-10","cited_by_count":14,"area":null},{"id":"2408.09764","title":"Event Stream based Human Action Recognition: A High-Definition Benchmark Dataset and Algorithms","created":"2024-08-19","cited_by_count":12,"area":null},{"id":"2408.17443","title":"HERMES: temporal-coHERent long-forM understanding with Episodes and Semantics","created":"2024-08-30","cited_by_count":11,"area":null},{"id":"2403.08330","title":"Activating Wider Areas in Image Super-Resolution","created":"2024-03-13","cited_by_count":10,"area":null},{"id":"2405.19723","title":"Encoding and Controlling Global Semantics for Long-form Video Question Answering","created":"2024-05-30","cited_by_count":8,"area":null},{"id":"2308.09775","title":"Long-range Multimodal Pretraining for Movie Understanding","created":"2023-08-18","cited_by_count":7,"area":null},{"id":"2309.11569","title":"Revisiting Kernel Temporal Segmentation as an Adaptive Tokenizer for Long-form Video Understanding","created":"2023-09-20","cited_by_count":7,"area":null},{"id":"2411.12593","title":"AdaCM$^2$: On Understanding Extremely Long-Term Video with Adaptive Cross-Modality Memory Reduction","created":"2024-11-19","cited_by_count":7,"area":null},{"id":"2308.11244","title":"Are current long-term video understanding datasets long-term?","created":"2023-08-22","cited_by_count":6,"area":null},{"id":"2412.06182","title":"Towards Long Video Understanding via Fine-detailed Video Story Generation","created":"2024-12-09","cited_by_count":6,"area":null},{"id":"2503.14237","title":"Make Your Training Flexible: Towards Deployment-Efficient Video Models","created":"2025-03-18","cited_by_count":6,"area":null},{"id":"2412.14294","title":"TRecViT: A Recurrent Video Transformer","created":"2024-12-18","cited_by_count":5,"area":null},{"id":"2304.05600","title":"Looking Similar, Sounding Different: Leveraging Counterfactual Cross-Modal Pairs for Audiovisual Representation Learning","created":"2023-04-12","cited_by_count":3,"area":null},{"id":"2310.08032","title":"Incorporating Domain Knowledge Graph into Multimodal Movie Genre Classification with Self-Supervised Attention and Contrastive Learning","created":"2023-10-12","cited_by_count":3,"area":null},{"id":"2411.13683","title":"Extending Video Masked Autoencoders to 128 frames","created":"2024-11-20","cited_by_count":3,"area":null},{"id":"2412.10002","title":"NowYouSee Me: Context-Aware Automatic Audio Description","created":"2024-12-13","cited_by_count":3,"area":null},{"id":"2504.03501","title":"LV-MAE: Learning Long Video Representations through Masked-Embedding Autoencoders","created":"2025-04-04","cited_by_count":3,"area":null},{"id":"2509.12069","title":"U-Mamba2: Scaling State Space Models for Dental Anatomy Segmentation in CBCT","created":"2025-09-15","cited_by_count":3,"area":null},{"id":"2603.24539","title":"CliPPER: Contextual Video-Language Pretraining on Long-form Intraoperative Surgical Procedures for Event Recognition","created":"2026-03-25","cited_by_count":3,"area":null},{"id":"2211.17042","title":"Spatio-Temporal Crop Aggregation for Video Representation Learning","created":"2022-11-30","cited_by_count":2,"area":null},{"id":"2401.12419","title":"Multi-modal News Understanding with Professionally Labelled Videos (ReutersViLNews)","created":"2024-01-23","cited_by_count":2,"area":null},{"id":"2503.11224","title":"Technologies on Effectiveness and Efficiency: A Survey of State Spaces Models","created":"2025-03-14","cited_by_count":2,"area":null},{"id":"2510.22951","title":"Hankel Singular Value Regularization for Highly Compressible State Space Models","created":"2025-10-27","cited_by_count":2,"area":null},{"id":"2311.18773","title":"Spacewalk-18: A Benchmark for Multimodal and Long-form Procedural Video Understanding in Novel Domains","created":"2023-11-30","cited_by_count":1,"area":null},{"id":"2405.11487","title":"\"Previously on ...\" From Recaps to Story Summarization","created":"2024-05-19","cited_by_count":1,"area":null},{"id":"2410.09844","title":"HASN: Hybrid Attention Separable Network for Efficient Image Super-resolution","created":"2024-10-13","cited_by_count":1,"area":null},{"id":"2412.07704","title":"GEXIA: Granularity Expansion and Iterative Approximation for Scalable Multi-grained Video-language Learning","created":"2024-12-10","cited_by_count":1,"area":null},{"id":"2503.16091","title":"AIMI: Leveraging Future Knowledge and Personalization in Sparse Event Forecasting for Treatment Adherence","created":"2025-03-20","cited_by_count":1,"area":null},{"id":"2507.06603","title":"Cross-Modal Dual-Causal Learning for Long-Term Action Recognition","created":"2025-07-09","cited_by_count":1,"area":null},{"id":"2508.05138","title":"Deep Learning-based Animal Behavior Analysis: Insights from Mouse Chronic Pain Models","created":"2025-08-07","cited_by_count":1,"area":null},{"id":"2605.08073","title":"EmambaIR: Efficient Visual State Space Model for Event-guided Image Reconstruction","created":"2026-05-08","cited_by_count":1,"area":null},{"id":"2609.01725","title":"From Visual Cues to Spoken Narration: Rethinking Audio Description","created":"2026-09-01","cited_by_count":1,"area":null},{"id":"2310.12724","title":"Query-aware Long Video Localization and Relation Discrimination for Deep Video Understanding","created":"2023-10-19","cited_by_count":0,"area":null},{"id":"2407.19201","title":"Long Range Switching Time Series Prediction via State Space Model","created":"2024-07-27","cited_by_count":0,"area":null},{"id":"2504.12513","title":"AdaVid: Adaptive Video-Language Pretraining","created":"2025-04-16","cited_by_count":0,"area":null},{"id":"2506.18544","title":"Normality Prior Guided Multi-Semantic Fusion Network for Unsupervised Image Anomaly Detection","created":"2025-06-23","cited_by_count":0,"area":null},{"id":"2509.03426","title":"Time-Scaling State-Space Models for Dense Video Captioning","created":"2025-09-03","cited_by_count":0,"area":null},{"id":"2509.09151","title":"Video Understanding by Design: How Datasets Shape Video Models","created":"2025-09-11","cited_by_count":0,"area":null},{"id":"2609.09711","title":"VFNet: Multi-View Spatio-Temporal Model for Void Fraction Estimation in Gas-Liquid Two-Phase Flow","created":"2026-09-09","cited_by_count":0,"area":null}],"next_cursor":null}