Browse State-of-the-Art › Referring Expression Segmentation

Referring Expression Segmentation

97 papers with code · 22 benchmarks · 11 datasets archive 2025-07-28

Computer Vision

The task aims at labeling the pixels of an image or video that represent an object instance referred by a linguistic expression. In particular, the referring expression (RE) must allow the identification of an individual object in a discourse or scene (the referent). REs unambiguously identify the target instance.

Description from the archive archive 2025-07-28.

Benchmarks archive 2025-07-28

22 leaderboard tables shown for this task, 22 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted. 10 shown of 22 until expanded.

Syntology 7 newer papers were judged to report on this task's benchmarks so far (Claude Sonnet 4.5, reading their tables: a model's judgement, not a result; 0 placed): RefCoCo val (7 judged, 0 placed), RefCOCO+ testA (5 judged, 0 placed), RefCOCO+ test B (5 judged, 0 placed), RefCOCOg-val (1 judged, 0 placed), RefCOCO testA (4 judged, 0 placed), RefCOCO testB (4 judged, 0 placed), RefCOCO (1 judged, 0 placed). Drawn from 8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read).

DatasetBest model (first row in archive order)PaperCodeSyntologyCompare
RefCoCo val (37 rows) DeRIS-L DeRIS: Decoupling Perception and Cognition for Enhanced Referring... code — Compare
RefCOCO+ val (33 rows) MLCD-Seg-7B Multi-label Cluster Discrimination for Visual Representation Learning code Syntology official (archive's flag): 7 ran · 7 ran (of which 7 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified; every one of the 7 samples that ran constructed an object rather than computing a result Compare
Refer-YouTube-VOS (2021 public validation) (33 rows) MPG-SAM 2 MPG-SAM 2: Adapting SAM 2 with Mask Priors and Global Context for... code Syntology official (archive's flag): 10 ran · 10 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 1 violated, 4 with no contract checked; 4 where Syntology's instrument failed) · 6 unverified Compare
RefCOCO+ testA (30 rows) HyperSeg HyperSeg: Towards Universal Visual Segmentation with Large Language Model code Syntology official (archive's flag): 13 ran · 13 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 4 honoured, 2 violated, 2 with no contract checked; 5 where Syntology's instrument failed) · 4 unverified Compare
RefCOCO+ test B (30 rows) MLCD-Seg-7B Multi-label Cluster Discrimination for Visual Representation Learning code Syntology official (archive's flag): 7 ran · 7 ran (of which 7 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified; every one of the 7 samples that ran constructed an object rather than computing a result Compare
A2D Sentences (27 rows) SgMg (Video-Swin-B) Spectrum-guided Multi-granularity Referring Video Object Segmentation code Syntology official (archive's flag): 6 ran · 6 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified Compare
RefCOCOg-val (23 rows) MLCD-Seg-7B Multi-label Cluster Discrimination for Visual Representation Learning code Syntology official (archive's flag): 7 ran · 7 ran (of which 7 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified; every one of the 7 samples that ran constructed an object rather than computing a result Compare
J-HMDB (21 rows) SgMg (Video-Swin-B) Spectrum-guided Multi-granularity Referring Video Object Segmentation code Syntology official (archive's flag): 6 ran · 6 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified Compare
DAVIS 2017 (val) (18 rows) UNINEXT-H Universal Instance Perception as Object Discovery and Retrieval code Syntology official (archive's flag): 4 ran · 4 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified Compare
RefCOCOg-test (18 rows) UniLSeg-100 Universal Segmentation at Arbitrary Granularity with Language Instruction code Syntology official (archive's flag): 14 ran · 14 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 12 where Syntology's instrument failed) · 2 unverified Compare
RefCOCO testA (13 rows) DeRIS-L DeRIS: Decoupling Perception and Cognition for Enhanced Referring... code — Compare
RefCOCO testB (13 rows) HyperSeg HyperSeg: Towards Universal Visual Segmentation with Large Language Model code Syntology official (archive's flag): 13 ran · 13 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 4 honoured, 2 violated, 2 with no contract checked; 5 where Syntology's instrument failed) · 4 unverified Compare
PhraseCut (6 rows) GLIPv2 GLIPv2: Unifying Localization and Vision-Language Understanding code Syntology official (archive's flag): 2 ran · 2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified Compare
RefCOCO (4 rows) DETRIS Densely Connected Parameter-Efficient Tuning for Referring Image... code Syntology official (archive's flag): 13 ran · 13 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 9 where Syntology's instrument failed) · 4 unverified Compare
ReferIt (3 rows) PolyFormer-L PolyFormer: Referring Image Segmentation as Sequential Polygon Generation code Syntology official (archive's flag): 5 ran · 5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified Compare
Refer-YouTube-VOS (2 rows) RefVOS-Human REs SynthRef: Generation of Synthetic Referring Expressions for Object... code — Compare
Referring Expressions for DAVIS 2016 & 2017 (1 row) MUTR Referred by Multi-Modality: A Unified Temporal Transformer for... code — Compare
A2Dre test (1 row) RefVos RefVOS: A Closer Look at Referring Expressions for Video Object... code — Compare
CLEVR-Ref+ (1 row) IEP-Ref (700K prog.) CLEVR-Ref+: Diagnosing Visual Reasoning with Referring Expressions code Syntology 4 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified Compare
G-Ref val (1 row) MaIL MaIL: A Unified Mask-Image-Language Trimodal Network for Referring... — — Compare
G-Ref test A (1 row) MaIL MaIL: A Unified Mask-Image-Language Trimodal Network for Referring... — — Compare
G-Ref test B (1 row) MaIL MaIL: A Unified Mask-Image-Language Trimodal Network for Referring... — — Compare

Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. Each line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the row's paper, the line starts with that repository's state (“official” is the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from. A dash means no Syntology record for that paper, not a recorded non-run. Each “ran” line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.

Libraries

Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.

Datasets archive 2025-07-28

11 datasets whose archive record lists this task, ordered by the archive's paper count.

Subtasks archive 2025-07-28

2 subtasks in the archive's task tree.

Parent tasks archive 2025-07-28

Papers archive 2025-07-28

archive papers tagged: 145 · with a code link: 97 · where Syntology ran a sample: 48 (42 with a run with no instrument failure, 6 where every run was a failure of Syntology's instrument) Syntology

Show: all tagged papersonly where code ran (48 of 145 tagged: 42 with a run with no instrument failure, 6 where every run was a failure of Syntology's instrument)

Page 1 of 2: papers 1 to 100 of 145, in archive order: by repositories listed in the archive (most first), then newest first, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers that list no repository come after every paper that lists one.

Papers without a page here are shown as plain text. A Syntology line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the figure “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code); hover it for the repositories the samples that ran came from. The first sentence of the abstract is shown for the first 30 papers; every abstract is on its paper's page.

Syntology lines on 50 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced; each line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections