Papers › MPG-SAM 2: Adapting SAM 2 with Mask Priors and Global Context for Referring Video...

MPG-SAM 2: Adapting SAM 2 with Mask Priors and Global Context for Referring Video Object Segmentation

23 Jan 2025arXiv:2501.13667archive 2025-07-28

Fu Rong, Meng Lan, Qian Zhang, Lefei Zhang

Referring video object segmentation (RVOS) aims to segment objects in a video according to textual descriptions, which requires the integration of multimodal information and temporal dynamics perception. The Segment Anything Model 2 (SAM 2) has shown great effectiveness across various video segmentation tasks. However, its application to offline RVOS is challenged by the translation of the text into effective prompts and a lack of global context awareness. In this paper, we propose a novel RVOS framework, termed MPG-SAM 2, to address these challenges. Specifically, MPG-SAM 2 employs a unified multimodal encoder to jointly encode video and textual features, generating semantically aligned video and text embeddings, along with multimodal class tokens. A mask prior generator utilizes the video embeddings and class tokens to create pseudo masks of target objects and global context. These masks are fed into the prompt encoder as dense prompts along with multimodal class tokens as sparse prompts to generate accurate prompts for SAM 2. To provide the online SAM 2 with a global view, we introduce a hierarchical global-historical aggregator, which allows SAM 2 to aggregate global and historical information of target objects at both pixel and object levels, enhancing the target representation and temporal consistency. Extensive experiments on several RVOS benchmarks demonstrate the superiority of MPG-SAM 2 and the effectiveness of our proposed modules.

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 16 code samples harvested from 1 repository linked to this paper: 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. Where Syntology's instrument failed: 3 where our contract draft was wrong; 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 16 samples from 1 repository, 10 ran (6 with no instrument failure; 4 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written between 2026-09-22 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

rongfu-dsb/MPG-SAM2 officialmentioned on GitHubpytorchApache-2.0Syntology: 16 samples, 10 ran (4 instrument-failed) · 6 unverified report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

16 samples harvested: 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. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · honoured contract
1ran · violated contract
3ran · our draft was wrong
1ran; the contract check could not run
4ran
6unverified

Licence: 1 of the 16 samples is pointer only, meaning Syntology does not serve that copy's text. For that sample, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from rongfu-dsb/MPG-SAM2. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

rongfu-dsb/MPG-SAM2 official repository 16 samples, 10 ran (4 instrument-failed) · 6 unverified
compute_axial_cis in 17 papers models/sam2/modeling/position_encoding.py ran · violated contract Apache-2.0 (permissive) · 7ceaad42da42edd5 · report fixture: signature dim:int/0/int, end_x:int/0/int, end_y:int/0/int, theta:float/0/float · returned Tensor · level recorded 2026-09-22
get_1d_sine_pe in 9 papers models/sam2/modeling/sam2_utils.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · a6c3974188a5ffb0 · report fixture: signature pos_inds:Tensor/1/int, dim:int/0/int, temperature:int/0/int · returned Tensor · level recorded 2026-09-22
get_activation_fn in 67 papers models/sam2/modeling/sam2_utils.py ran · our draft was wrong Apache-2.0 (permissive) here; the stored copy is pointer only · f2e72d81f39d65cd · report fixture: signature activation:str/0/str · returned function · level recorded 2026-09-25
init_t_xy in 15 papers models/sam2/modeling/position_encoding.py ran · honoured contract fingerprinted Apache-2.0 (permissive) · bb060d29525f90eb · report fixture: signature end_x:int/0/int, end_y:int/0/int · returned tuple · level recorded 2026-09-22
is_box_near_crop_edge in 7 papers models/sam2/utils/amg.py ran Apache-2.0 (permissive) · 3aac722b6505ee55 · report fixture: signature boxes:Tensor/2/float, crop_box:list/1/int, orig_box:list/1/int, atol:float/0/float · returned Tensor · level recorded 2026-09-25
load_video_frames models/sam2/utils/misc.py ran Apache-2.0 (permissive) · 5cc4935655a7476a · report fixture: signature video_path:str/0/str, image_size:int/0/int, offload_video_to_cpu:bool/0/bool, img_mean:tuple/1/float, img_std:tuple/1/float, async_loading_frames:bool/0/bool, compute_device:device/0/? · returned tuple · level recorded 2026-09-24
mask_to_box models/sam2/utils/misc.py ran Apache-2.0 (permissive) · b91b1a2983dbf738 · report fixture: signature masks:Tensor/4/bool · returned Tensor · level recorded 2026-09-24
mask_to_rle_pytorch in 9 papers models/sam2/utils/amg.py ran Apache-2.0 (permissive) · bfa3b8111ef40247 · report fixture: signature tensor:Tensor/3/int · returned list · level recorded 2026-09-24
reshape_for_broadcast in 90 papers
census: 6 implementations from 10 papers, 1 distinct output on one shared input this sample: bucket 1 of 1, arg 1: rank 2, kind float, dtype float32 · arg 2: rank 3, kind float, dtype float32
models/sam2/modeling/position_encoding.py ran; the contract check could not run (RAISES) fingerprinted Apache-2.0 (permissive) · f8f09f78b474ee7c · report fixture: signature freqs_cis:Tensor/2/float, x:Tensor/3/float · returned Tensor · level recorded 2026-09-22
select_closest_cond_frames in 9 papers models/sam2/modeling/sam2_utils.py ran · our draft was wrong Apache-2.0 (permissive) · 4ee20f090e58c425 · report fixture: signature frame_idx:int/0/int, cond_frame_outputs:dict/0/?, max_cond_frame_num:int/0/int · returned tuple · level recorded 2026-09-22
box_xyxy_to_xywh in 19 papers models/sam2/utils/amg.py unverified Apache-2.0 (permissive) · ca78fd1ad096a766 · report
build_sam2 in 17 papers models/sam2/build_sam.py unverified Apache-2.0 (permissive) · df0caf7e54b2c61e · report
build_sam2_hf in 9 papers models/sam2/build_sam.py unverified Apache-2.0 (permissive) · c83fb75d631af894 · report
build_sam2_video_predictor in 15 papers models/sam2/build_sam.py unverified Apache-2.0 (permissive) · b6bf96dd6b61e154 · report
get_connected_components models/sam2/utils/misc.py unverified Apache-2.0 (permissive) · baff5f8846f48223 · report
parse_args in 355 papers merge_lora_weights_and_save_hf_model.py unverified Apache-2.0 (permissive) · 77c6e8c3acbaea40 · report

Tasks

Referring Expression SegmentationReferring Video Object SegmentationSemantic SegmentationVideo Object SegmentationVideo SegmentationVideo Semantic Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Referring Expression Segmentation Refer-YouTube-VOS (2021 public validation) MPG-SAM 2 F 76.1 #1 of 33 Archive leaderboard report
Referring Expression Segmentation Refer-YouTube-VOS (2021 public validation) MPG-SAM 2 J 71.7 #1 of 33 Archive leaderboard report
Referring Expression Segmentation Refer-YouTube-VOS (2021 public validation) MPG-SAM 2 J&F 73.9 #1 of 33 Archive leaderboard report
Referring Video Object Segmentation MeViS MPG-SAM 2 F 56.7 #1 of 16 Archive leaderboard report
Referring Video Object Segmentation MeViS MPG-SAM 2 J 50.7 #1 of 16 Archive leaderboard report
Referring Video Object Segmentation MeViS MPG-SAM 2 J&F 53.7 #1 of 16 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

SAM

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