AI Paper Atlas

Research map / Benchmarks / Ref-DAVIS17

Ref-DAVIS17 leaderboard

33 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on Ref-DAVIS17. Best J&F: 80.6 (Ours (EVOG), NeurIPS 2026).

Numbers are as each paper reports them, read by AI from its results tables and not checked by hand. Papers can differ in setting (training data, model size, extra data); the topic column shows what each paper is about. Open the paper before you compare or quote a number.

Ref-DAVIS17 · J&F

33 papers, each with its best reported number for its own method; higher is better.

#J&F ↑MethodPaperTopic
180.6Ours (EVOG)
Qwen2.5-VL-7B
Beyond Token Representations: Explicit Visual Object Grounding for Video Reasoning Segmentation
NeurIPS 2026 · Table 2
Video segmentation and tracking
280VideoSEG-O3-2B
Qwen3-VL-2B
VideoSEG-O3: A Multi-turn Reinforcement Learning Framework for Reasoning Video Object Segmentation
ICML 2026 · Table 1
Video-language understanding
379.8VideoSeg-R1
Qwen2.5-VL-7B
VideoSeg-R1:Reasoning Video Object Segmentation via Reinforcement Learning
AAAI 2026 · Table 1
Video-language understanding
477.4MomentSeg-7BMomentSeg: Moment-Centric Sampling for Enhanced Referring Video Object Segmentation
ECCV 2026 · Table 3
Video segmentation and tracking
577.3SAMA-8B
Sa2VA-8B
SAMA: Towards Multi-Turn Referential Grounded Video Chat with Large Language Models
NeurIPS 2025 · Table 2
Video-language understanding
677Sa2VA-26BSa2VA: Marrying SAM2 With MLLM for Dense Grounded Understanding of Images and Videos
TPAMI 2026 · Table 5/Table 12
Video-language understanding
777DeSa2VA-4B
InternVL2.5-4b
Decoupled Seg Tokens Make Stronger Reasoning Video Segmenter and Grounder
TPAMI 2026 · Table 1
Video-language understanding
876.6StreamingRVOS-4BTowards Streaming Referring Video Segmentation via Large Language Model
CVPR 2026 · Table 1
Video segmentation and tracking
976.3Sa2VA* (motion-centric LoRA)
InternVL2.5-8B
PixFoundation 2.0: Do Video Multi-Modal LLMs Use Motion in Visual Grounding?
NeurIPS 2026 · Table 2
Video-language understanding
1074.88DTOS-9B
VILA1.5-LLaMA3-8B
DTOS: Dynamic Time Object Sensing with Large Multimodal Model
CVPR 2025 · Table 1
Video-language understanding
23 more papers on this leaderboard, the baselines reported on it and a CSV download are free with a scime account.
Sign in free to see all

Not affiliated with any conference, journal or the benchmark's authors. Corrections: contact@latenticlabs.com.