{"list":"other","total":64,"rows":[{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"2312.00752","title":"Mamba: Linear-Time Sequence Modeling with Selective State Spaces","created":"2023-12-01","cited_by_count":4718},{"id":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"id":"2004.11362","title":"Supervised Contrastive Learning","created":"2020-04-23","cited_by_count":2829},{"id":"2311.15127","title":"Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets","created":"2023-11-25","cited_by_count":2581},{"id":"2003.12039","title":"RAFT: Recurrent All-Pairs Field Transforms for Optical Flow","created":"2020-03-26","cited_by_count":2415},{"id":"1705.06950","title":"The Kinetics Human Action Video Dataset","created":"2017-05-19","cited_by_count":1909},{"id":"1812.03982","title":"SlowFast Networks for Video Recognition","created":"2018-12-10","cited_by_count":1867},{"id":"2106.13230","title":"Video Swin Transformer","created":"2021-06-24","cited_by_count":1091},{"id":"1904.08405","title":"Event-based Vision: A Survey","created":"2019-04-17","cited_by_count":1016},{"id":"2205.15868","title":"CogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformers","created":"2022-05-29","cited_by_count":985},{"id":"1811.08383","title":"TSM: Temporal Shift Module for Efficient Video Understanding","created":"2018-11-20","cited_by_count":856},{"id":"2303.13439","title":"Text2Video-Zero: Text-to-Image Diffusion Models are Zero-Shot Video Generators","created":"2023-03-23","cited_by_count":670},{"id":"2308.06571","title":"ModelScope Text-to-Video Technical Report","created":"2023-08-12","cited_by_count":658},{"id":"2412.20404","title":"Open-Sora: Democratizing Efficient Video Production for All","created":"2024-12-29","cited_by_count":652},{"id":"2004.04730","title":"X3D: Expanding Architectures for Efficient Video Recognition","created":"2020-04-09","cited_by_count":637},{"id":"1901.09948","title":"Surrogate Gradient Learning in Spiking Neural Networks","created":"2019-01-28","cited_by_count":626},{"id":"2302.03011","title":"Structure and Content-Guided Video Synthesis with Diffusion Models","created":"2023-02-06","cited_by_count":590},{"id":"2401.09047","title":"VideoCrafter2: Overcoming Data Limitations for High-Quality Video Diffusion Models","created":"2024-01-17","cited_by_count":579},{"id":"2401.03048","title":"Latte: Latent Diffusion Transformer for Video Generation","created":"2024-01-05","cited_by_count":546},{"id":"2310.19512","title":"VideoCrafter1: Open Diffusion Models for High-Quality Video Generation","created":"2023-10-30","cited_by_count":535},{"id":"2112.01526","title":"MViTv2: Improved Multiscale Vision Transformers for Classification and Detection","created":"2021-12-02","cited_by_count":519},{"id":"2307.06942","title":"InternVid: A Large-scale Video-Text Dataset for Multimodal Understanding and Generation","created":"2023-07-13","cited_by_count":497},{"id":"2309.15103","title":"LAVIE: High-Quality Video Generation with Cascaded Latent Diffusion Models","created":"2023-09-26","cited_by_count":349},{"id":"2007.05785","title":"Incorporating Learnable Membrane Time Constant to Enhance Learning of Spiking Neural Networks","created":"2020-07-11","cited_by_count":345},{"id":"2403.06977","title":"VideoMamba: State Space Model for Efficient Video Understanding","created":"2024-03-11","cited_by_count":328},{"id":"2208.02816","title":"Expanding Language-Image Pretrained Models for General Video Recognition","created":"2022-08-04","cited_by_count":321},{"id":"2403.15377","title":"InternVideo2: Scaling Foundation Models for Multimodal Video Understanding","created":"2024-03-22","cited_by_count":317},{"id":"1507.07629","title":"Converting Static Image Datasets to Spiking Neuromorphic Datasets Using Saccades","created":"2015-07-28","cited_by_count":314},{"id":"2309.15818","title":"Show-1: Marrying Pixel and Latent Diffusion Models for Text-to-Video Generation","created":"2023-09-27","cited_by_count":302},{"id":"2209.15425","title":"Spikformer: When Spiking Neural Network Meets Transformer","created":"2022-09-29","cited_by_count":271},{"id":"2310.20700","title":"SEINE: Short-to-Long Video Diffusion Model for Generative Transition and Prediction","created":"2023-10-31","cited_by_count":233},{"id":"2310.16620","title":"SpikingJelly: An open-source machine learning infrastructure platform for spike-based intelligence","created":"2023-10-25","cited_by_count":169},{"id":"2305.10874","title":"Swap Attention in Spatiotemporal Diffusions for Text-to-Video Generation","created":"2023-05-18","cited_by_count":154},{"id":"2307.01694","title":"Spike-driven Transformer","created":"2023-07-04","cited_by_count":146},{"id":"2005.01807","title":"Enabling Deep Spiking Neural Networks with Hybrid Conversion and Spike Timing Dependent Backpropagation","created":"2020-05-04","cited_by_count":144},{"id":"2307.07494","title":"TALL: Thumbnail Layout for Deepfake Video Detection","created":"2023-07-14","cited_by_count":100},{"id":"1811.08230","title":"Event-based High Dynamic Range Image and Very High Frame Rate Video Generation using Conditional Generative Adversarial Networks","created":"2018-11-20","cited_by_count":97},{"id":"2405.19707","title":"DeMamba: AI-Generated Video Detection on Million-Scale GenVideo Benchmark","created":"2024-05-30","cited_by_count":92},{"id":"2109.01860","title":"Spatiotemporal Inconsistency Learning for DeepFake Video Detection","created":"2021-09-04","cited_by_count":88},{"id":"2406.06040","title":"Vript: A Video Is Worth Thousands of Words","created":"2024-06-10","cited_by_count":71},{"id":"2408.13627","title":"Recent Event Camera Innovations: A Survey","created":"2024-08-24","cited_by_count":68},{"id":"2201.10943","title":"Event-based Video Reconstruction via Potential-assisted Spiking Neural Network","created":"2022-01-25","cited_by_count":59},{"id":"2411.16061","title":"Scaling Spike-driven Transformer with Efficient Spike Firing Approximation Training","created":"2024-11-25","cited_by_count":59},{"id":"2304.01230","title":"SEENN: Towards Temporal Spiking Early-Exit Neural Networks","created":"2023-04-02","cited_by_count":41},{"id":"2312.10461","title":"Rethinking the Up-Sampling Operations in CNN-based Generative Network for Generalizable Deepfake Detection","created":"2023-12-16","cited_by_count":41},{"id":"2410.23623","title":"On Learning Multi-Modal Forgery Representation for Diffusion Generated Video Detection","created":"2024-10-31","cited_by_count":40},{"id":"2310.06232","title":"Spiking PointNet: Spiking Neural Networks for Point Clouds","created":"2023-10-10","cited_by_count":34},{"id":"2506.00979","title":"Ivy-Fake: A Unified Explainable Framework and Benchmark for Image and Video AIGC Detection","created":"2025-06-01","cited_by_count":34},{"id":"2507.00583","title":"AI-Generated Video Detection via Perceptual Straightening","created":"2025-07-01","cited_by_count":34},{"id":"2508.00701","title":"D3: Training-Free AI-Generated Video Detection Using Second-Order Features","created":"2025-08-01","cited_by_count":34},{"id":"2510.08073","title":"Physics-Driven Spatiotemporal Modeling for AI-Generated Video Detection","created":"2025-10-09","cited_by_count":27},{"id":"2402.02085","title":"Detecting AI-Generated Video via Frame Consistency","created":"2024-02-03","cited_by_count":26},{"id":"2501.11340","title":"GenVidBench: A 6-Million Benchmark for AI-Generated Video Detection","created":"2025-01-20","cited_by_count":25},{"id":"2503.12905","title":"UCF-Crime-DVS: A Novel Event-Based Dataset for Video Anomaly Detection with Spiking Neural Networks","created":"2025-03-17","cited_by_count":19},{"id":"2208.02253","title":"LaneSNNs: Spiking Neural Networks for Lane Detection on the Loihi Neuromorphic Processor","created":"2022-08-03","cited_by_count":10},{"id":"2407.14073","title":"LoAS: Fully Temporal-Parallel Dataflow for Dual-Sparse Spiking Neural Networks","created":"2024-07-19","cited_by_count":8},{"id":"2309.10987","title":"SpikingNeRF: Making Bio-inspired Neural Networks See through the Real World","created":"2023-09-20","cited_by_count":6},{"id":"2502.09449","title":"Spiking Neural Networks for Temporal Processing: Status Quo and Future Prospects","created":"2025-02-13","cited_by_count":6},{"id":"2503.05108","title":"TS-LIF: A Temporal Segment Spiking Neuron Network for Time Series Forecasting","created":"2025-03-07","cited_by_count":6},{"id":"2505.10352","title":"SpikeVideoFormer: An Efficient Spike-Driven Video Transformer with Hamming Attention and $\\mathcal{O}(T)$ Complexity","created":"2025-05-15","cited_by_count":4},{"id":"2506.07720","title":"ReverB-SNN: Reversing Bit of the Weight and Activation for Spiking Neural Networks","created":"2025-06-09","cited_by_count":3},{"id":"2412.09881","title":"Sharpening Your Density Fields: Spiking Neuron Aided Fast Geometry Learning","created":"2024-12-13","cited_by_count":2},{"id":"2512.05472","title":"Unleashing Temporal Capacity of Spiking Neural Networks through Spatiotemporal Separation","created":"2025-12-05","cited_by_count":1}],"next_cursor":null}