{"total":65,"rows":[{"id":"2512.10863","title":"MMSI-Video-Bench: A Holistic Benchmark for Video-Based Spatial Intelligence","created":"2025-12-11","cited_by_count":38,"area":null},{"id":"2503.09146","title":"Generative Frame Sampler for Long Video Understanding","created":"2025-03-12","cited_by_count":37,"area":null},{"id":"2507.13353","title":"VideoITG: Multimodal Video Understanding with Instructed Temporal Grounding","created":"2025-07-17","cited_by_count":29,"area":null},{"id":"2603.02096","title":"FluxMem: Adaptive Hierarchical Memory for Streaming Video Understanding","created":"2026-03-02","cited_by_count":28,"area":null},{"id":"2510.12422","title":"VideoLucy: Deep Memory Backtracking for Long Video Understanding","created":"2025-10-14","cited_by_count":22,"area":null},{"id":"2508.09486","title":"Video-EM: Event-Centric Episodic Memory for Long-Form Video Understanding","created":"2025-08-13","cited_by_count":10,"area":null},{"id":"2510.02262","title":"From Frames to Clips: Training-free Adaptive Key Clip Selection for Long-Form Video Understanding","created":"2025-10-02","cited_by_count":9,"area":null},{"id":"2510.02778","title":"AdaRD-key: Adaptive Relevance-Diversity Keyframe Sampling for Long-form Video understanding","created":"2025-10-03","cited_by_count":9,"area":null},{"id":"2512.14273","title":"Zoom-Zero: Reinforced Coarse-to-Fine Video Understanding via Temporal Zoom-in","created":"2025-12-16","cited_by_count":8,"area":null},{"id":"2602.20913","title":"LongVideo-R1: Smart Navigation for Low-cost Long Video Understanding","created":"2026-02-24","cited_by_count":7,"area":null},{"id":"2606.02569","title":"AdaCodec: A Predictive Visual Code for Video MLLMs","created":"2026-06-01","cited_by_count":7,"area":null},{"id":"2512.14017","title":"KFS-Bench: Comprehensive Evaluation of Key Frame Sampling in Long Video Understanding","created":"2025-12-16","cited_by_count":6,"area":null},{"id":"2510.20622","title":"SeViCES: Unifying Semantic-Visual Evidence Consensus for Long Video Understanding","created":"2025-10-23","cited_by_count":5,"area":null},{"id":"2509.20851","title":"Poisoning Prompt-Guided Sampling in Video Large Language Models","created":"2025-09-25","cited_by_count":4,"area":null},{"id":"2510.11129","title":"video-SALMONN S: Memory-Enhanced Streaming Audio-Visual LLM","created":"2025-10-13","cited_by_count":4,"area":null},{"id":"2510.23928","title":"Adaptive Keyframe Selection for Scalable 3D Scene Reconstruction in Dynamic Environments","created":"2025-10-27","cited_by_count":4,"area":null},{"id":"2512.14870","title":"HERBench: A Benchmark for Multi-Evidence Integration in Video Question Answering","created":"2025-12-16","cited_by_count":4,"area":null},{"id":"2603.22120","title":"StreamingClaw Technical Report","created":"2026-03-23","cited_by_count":4,"area":null},{"id":"2510.04022","title":"Video-in-the-Loop: Span-Grounded Long Video QA with Interleaved Reasoning","created":"2025-10-05","cited_by_count":3,"area":null},{"id":"2511.18831","title":"VideoCompressa: Data-Efficient Video Understanding via Joint Temporal Compression and Spatial Reconstruction","created":"2025-11-24","cited_by_count":3,"area":null},{"id":"2601.20297","title":"Artifact-Aware Evaluation for High-Quality Video Generation","created":"2026-01-28","cited_by_count":3,"area":null},{"id":"2603.04349","title":"FocusGraph: Graph-Structured Frame Selection for Embodied Long Video Question Answering","created":"2026-03-04","cited_by_count":3,"area":null},{"id":"2603.23186","title":"ViKey: Enhancing Temporal Understanding in Videos via Visual Prompting","created":"2026-03-24","cited_by_count":3,"area":null},{"id":"2609.00291","title":"StreamScout: Learning When to Look Deeper for Streaming Video Understanding","created":"2026-08-31","cited_by_count":3,"area":null},{"id":"2508.13692","title":"HumanPCR: Probing MLLM Capabilities in Diverse Human-Centric Scenes","created":"2025-08-19","cited_by_count":2,"area":null},{"id":"2509.08016","title":"Video Parallel Scaling: Aggregating Diverse Frame Subsets for VideoLLMs","created":"2025-09-09","cited_by_count":2,"area":null},{"id":"2605.22678","title":"Swift Sampling: Selecting Temporal Surprises via Taylor Series","created":"2026-05-21","cited_by_count":2,"area":null},{"id":"2606.27922","title":"Reflect-R1: Evidence-Driven Reflection for Self-Correction in Long Video Understanding","created":"2026-06-26","cited_by_count":2,"area":null},{"id":"2608.22516","title":"TRACE: Temporal Retrieval with Anchored and Convergent Evidence for Long-Horizon Video Understanding","created":"2026-08-23","cited_by_count":2,"area":null},{"id":"2503.21782","title":"Mobile-VideoGPT: Fast and Accurate Model for Mobile Video Understanding","created":"2025-03-27","cited_by_count":1,"area":null},{"id":"2509.23433","title":"SPIKE-RL: Video-LLMs meet Bayesian Surprise","created":"2025-09-27","cited_by_count":1,"area":null},{"id":"2510.06509","title":"From Captions to Keyframes: KeyScore for Multimodal Frame Scoring and Video-Language Understanding","created":"2025-10-07","cited_by_count":1,"area":null},{"id":"2512.11534","title":"HFS: Holistic Query-Aware Frame Selection for Efficient Video Understanding","created":"2025-12-12","cited_by_count":1,"area":null},{"id":"2601.14594","title":"LFS: Learnable Frame Selector for Event-Aware and Temporally Diverse Video Captioning","created":"2026-01-21","cited_by_count":1,"area":null},{"id":"2602.10639","title":"VideoSTF: Stress-Testing Output Repetition in Video Large Language Models","created":"2026-02-11","cited_by_count":1,"area":null},{"id":"2603.20180","title":"Adaptive Greedy Frame Selection for Long Video Understanding","created":"2026-03-20","cited_by_count":1,"area":null},{"id":"2604.07772","title":"ESOM: Efficiently Understanding Streaming Video Anomalies with Open-world Dynamic Definitions","created":"2026-04-09","cited_by_count":1,"area":null},{"id":"2605.23826","title":"Decomposing Queries into Tool Calls for Long-Video Keyframe Retrieval","created":"2026-05-22","cited_by_count":1,"area":null},{"id":"2606.20711","title":"Video2Code: Generating Interactive Webpages from UI Videos via Action-Aware Revisit","created":"2026-06-16","cited_by_count":1,"area":null},{"id":"2606.30026","title":"MuseBench: Benchmarking Intent-Level Audiovisual Arts Understanding in MLLMs","created":"2026-06-29","cited_by_count":1,"area":null},{"id":"2609.18540","title":"SVMemAgent: A Streaming Video Memory Agent for Query-Agnostic Online Frame Selection","created":"2026-09-16","cited_by_count":1,"area":null},{"id":"2510.18362","title":"FeatureFool: Zero-Query Fooling of Video Models via Feature Map","created":"2025-10-21","cited_by_count":0,"area":null},{"id":"2601.07459","title":"Improving Video Question Answering through query-based frame selection","created":"2026-01-12","cited_by_count":0,"area":null},{"id":"2601.13974","title":"STEC: A Reference-Free Spatio-Temporal Entropy Coverage Metric for Evaluating Sampled Video Frames","created":"2026-01-20","cited_by_count":0,"area":null},{"id":"2602.22299","title":"Decoding the Hook: A Multimodal LLM Framework for Analyzing the Hooking Period of Video Ads","created":"2026-02-25","cited_by_count":0,"area":null},{"id":"2603.00126","title":"QuickGrasp: Responsive Video-Language Querying Service via Accelerated Tokenization and Edge-Augmented Inference","created":"2026-02-23","cited_by_count":0,"area":null},{"id":"2603.12764","title":"SAVA-X: Ego-to-Exo Imitation Error Detection via Scene-Adaptive View Alignment and Bidirectional Cross View Fusion","created":"2026-03-13","cited_by_count":0,"area":null},{"id":"2604.08077","title":"AdaSpark: Adaptive Sparsity for Efficient Long-Video Understanding","created":"2026-04-09","cited_by_count":0,"area":null},{"id":"2604.11913","title":"V-Nutri: Dish-Level Nutrition Estimation from Egocentric Cooking Videos","created":"2026-04-13","cited_by_count":0,"area":null},{"id":"2606.06532","title":"GOPAgen: Codec-Aware Agentic Long-Video Understanding with Structured Memory","created":"2026-06-03","cited_by_count":0,"area":null},{"id":"2607.05516","title":"Statistical Adversaries: Natural Backdoor-like Adversarial Features in Clean Vision Datasets","created":"2026-07-06","cited_by_count":0,"area":null},{"id":"2607.15778","title":"Modularized Dynamic-Granularity Video LLM for Multi-Event Long Video Understanding","created":"2026-07-17","cited_by_count":0,"area":null},{"id":"2608.07932","title":"SportsGrounder: Proposal-Aided Interleaved Grounding for Dense Sports Video Reasoning","created":"2026-08-08","cited_by_count":0,"area":null},{"id":"2608.22359","title":"Pre-Decoding Acoustic Triage for Budgeted Vision-Language Captioning of Untrimmed Egocentric Video","created":"2026-08-23","cited_by_count":0,"area":null},{"id":"2608.27929","title":"Training-Free Temporal Abstraction for General Video Understanding","created":"2026-08-28","cited_by_count":0,"area":null},{"id":"2609.10355","title":"Why Is Video Still So Expensive? A Survey of Inference-Efficiency Mechanisms in Video and Audiovisual LLMs","created":"2026-09-09","cited_by_count":0,"area":null},{"id":"2609.24124","title":"ActiveArena: Benchmarking and Understanding Active Perception in Robotic Manipulation","created":"2026-09-21","cited_by_count":0,"area":null},{"id":"2609.31668","title":"Query-aligned video frame selection for long video understanding","created":"2026-09-15","cited_by_count":0,"area":null},{"id":"2609.32957","title":"DynamicDx: Evaluating Evidence Acquisition in Video-Based Diagnosis","created":"2026-09-26","cited_by_count":0,"area":null},{"id":"2609.33083","title":"dKFD: Phase-Structured Evidence Allocation for Fixed-Budget Localized Event Understanding","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2610.05526","title":"Have I Scene This Before? Spatially Grounded Conversational Memory for Complex Queries in Egocentric Assistants","created":"2026-10-04","cited_by_count":0,"area":null},{"id":"2610.13915","title":"Where to Look Matters: Rethinking Sub-Volume Sampling in 3D Medical Self-supervised Learning","created":"2026-10-09","cited_by_count":0,"area":null},{"id":"2610.16299","title":"Learning Temporal Evidence Selection for Video Anomaly Understanding","created":"2026-10-12","cited_by_count":0,"area":null},{"id":"2610.17098","title":"Contrastive learning for video reuse detection","created":"2026-10-12","cited_by_count":0,"area":null},{"id":"2610.19050","title":"Focus, Align, and Diffuse: Time-Series-Aware Keyframe Diffusion for Cardiac Dynamic Synthesis from Sparse Observations","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}