{"total":18,"rows":[{"id":"2507.11245","title":"NarrLV: Towards a Comprehensive Narrative-Centric Evaluation for Long Video Generation","created":"2025-07-15","cited_by_count":22,"area":null},{"id":"2405.19818","title":"WebUOT-1M: Advancing Deep Underwater Object Tracking with A Million-Scale Benchmark","created":"2024-05-30","cited_by_count":15,"area":null},{"id":"2410.02492","title":"DTVLT: A Multi-modal Diverse Text Benchmark for Visual Language Tracking Based on LLM","created":"2024-10-03","cited_by_count":12,"area":null},{"id":"2409.08887","title":"Visual Language Tracking with Multi-modal Interaction: A Robust Benchmark","created":"2024-09-13","cited_by_count":10,"area":null},{"id":"2411.15600","title":"How Texts Help? A Fine-grained Evaluation to Reveal the Role of Language in Vision-Language Tracking","created":"2024-11-23","cited_by_count":10,"area":null},{"id":"2505.19434","title":"CSTrack: Enhancing RGB-X Tracking via Compact Spatiotemporal Features","created":"2025-05-26","cited_by_count":10,"area":null},{"id":"2507.19875","title":"ATCTrack: Aligning Target-Context Cues with Dynamic Target States for Robust Vision-Language Tracking","created":"2025-07-26","cited_by_count":10,"area":null},{"id":"2412.19648","title":"Enhancing Vision-Language Tracking by Effectively Converting Textual Cues into Visual Cues","created":"2024-12-27","cited_by_count":8,"area":null},{"id":"2409.02370","title":"Do Large Language Models Possess Sensitive to Sentiment?","created":"2024-09-04","cited_by_count":3,"area":null},{"id":"2505.00752","title":"DARTer: Dynamic Adaptive Representation Tracker for Nighttime UAV Tracking","created":"2025-05-01","cited_by_count":3,"area":null},{"id":"2502.08905","title":"DiffoRA: Enabling Parameter-Efficient Fine-Tuning via Differential Module Selection","created":"2025-02-13","cited_by_count":2,"area":null},{"id":"2507.00454","title":"ATSTrack: Enhancing Visual-Language Tracking by Aligning Temporal and Spatial Scales","created":"2025-07-01","cited_by_count":2,"area":null},{"id":"2606.22631","title":"4DVLT: Dynamic Scene Understanding with Worldline-Centered Vision-Language Tracking","created":"2026-06-21","cited_by_count":2,"area":null},{"id":"2410.18701","title":"BATON: Enhancing Batch-wise Inference Efficiency for Large Language Models via Dynamic Re-batching","created":"2024-10-24","cited_by_count":1,"area":null},{"id":"2605.07064","title":"Learning to Track Instance from Single Nature Language Description","created":"2026-05-08","cited_by_count":1,"area":null},{"id":"2410.20340","title":"Maintaining Informative Coherence: Migrating Hallucinations in Large Language Models via Absorbing Markov Chains","created":"2024-10-27","cited_by_count":0,"area":null},{"id":"2508.09524","title":"SOI is the Root of All Evil: Quantifying and Breaking Similar Object Interference in Single Object Tracking","created":"2025-08-13","cited_by_count":0,"area":null},{"id":"2609.19022","title":"TalkMatrix: Generating Character Dialogue that is Both Consistent and Diverse","created":"2026-07-20","cited_by_count":0,"area":null}],"next_cursor":null}