Papers › Elysium: Exploring Object-level Perception in Videos via MLLM

Elysium: Exploring Object-level Perception in Videos via MLLM

25 Mar 2024arXiv:2403.16558archive 2025-07-28

Han Wang, Yanjie Wang, YongJie Ye, Yuxiang Nie, Can Huang

Multi-modal Large Language Models (MLLMs) have demonstrated their ability to perceive objects in still images, but their application in video-related tasks, such as object tracking, remains understudied. This lack of exploration is primarily due to two key challenges. Firstly, extensive pretraining on large-scale video datasets is required to equip MLLMs with the capability to perceive objects across multiple frames and understand inter-frame relationships. Secondly, processing a large number of frames within the context window of Large Language Models (LLMs) can impose a significant computational burden. To address the first challenge, we introduce ElysiumTrack-1M, a large-scale video dataset supported for three tasks: Single Object Tracking (SOT), Referring Single Object Tracking (RSOT), and Video Referring Expression Generation (Video-REG). ElysiumTrack-1M contains 1.27 million annotated video frames with corresponding object boxes and descriptions. Leveraging this dataset, we conduct training of MLLMs and propose a token-compression model T-Selector to tackle the second challenge. Our proposed approach, Elysium: Exploring Object-level Perception in Videos via MLLM, is an end-to-end trainable MLLM that attempts to conduct object-level tasks in videos without requiring any additional plug-in or expert models. All codes and datasets are available at https://github.com/Hon-Wong/Elysium.

PaperPDFCodeCode Syntology ran

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

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2403.16558")

Code

Syntology Ran 7 of 8 code samples harvested from 1 repository linked to this paper; 1 has no recorded run. Of those that ran: 7 ran with no contract checked.

By repository: official repository: 8 samples from 1 repository, 7 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

hon-wong/elysium officialmentioned in papermentioned on GitHubpytorch 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

8 samples harvested; 7 ran; 0 honoured the contract we drafted; 1 has no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

7ran
1unverified

Licence: 8 of the 8 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from hon-wong/elysium. “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. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (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 from a repository marked official are listed first. 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 four 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; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). 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.

b2str hon-wong/elysium/eval/merge_result.py official repository ran fingerprinted no licence file found · pointer only · 03ea4ef71d990d69 · report
build_adapter hon-wong/elysium/models/rantselector.py official repository ran no licence file found · pointer only · 14a5b06381b76869 · report
build_projector hon-wong/elysium/models/build_vit.py official repository ran no licence file found · pointer only · dc5f7a793bd5c8b8 · report
calc_err_center hon-wong/elysium/eval/otb.py official repository ran fingerprinted no licence file found · pointer only · 66f1707e5716c275 · report
calc_iou_overlap hon-wong/elysium/eval/otb.py official repository ran fingerprinted no licence file found · pointer only · 3079b3e29bfecb3d · report
calc_seq_err_robust hon-wong/elysium/eval/otb.py official repository ran no licence file found · pointer only · 30aa0d18d04fc6fb · report
parse_box_from_raw_text hon-wong/elysium/eval/merge_result.py official repository ran fingerprinted no licence file found · pointer only · 7f7a40ee6ae5eb93 · report
create_clip_vit hon-wong/elysium/models/build_vit.py official repository unverified no licence file found · pointer only · 69245b70a5e8929e · report

Tasks

ObjectObject TrackingReferring ExpressionReferring Expression ComprehensionReferring expression generationVideo Question AnsweringVisual Object TrackingZero-Shot Single Object TrackingZero-Shot Video Question Answer

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Zero-Shot Single Object Tracking LaSOT Elysium AUC 56.1 #2 of 2 Archive leaderboard report
Zero-Shot Single Object Tracking LaSOT Elysium Normalized Precision 61.0 #2 of 2 Archive leaderboard report
Zero-Shot Single Object Tracking LaSOT Elysium Precision 50.1 #2 of 2 Archive leaderboard report
Zero-Shot Video Question Answer ActivityNet-QA Elysium Accuracy 43.4 #23 of 28 Archive leaderboard report
Zero-Shot Video Question Answer ActivityNet-QA Elysium Confidence Score 2.9 #23 of 28 Archive leaderboard report
Zero-Shot Video Question Answer MSRVTT-QA Elysium Accuracy 67.5 #3 of 30 Archive leaderboard report
Zero-Shot Video Question Answer MSRVTT-QA Elysium Confidence Score 3.2 #3 of 30 Archive leaderboard report
Zero-Shot Video Question Answer MSVD-QA Elysium Accuracy 75.8 #10 of 28 Archive leaderboard report
Zero-Shot Video Question Answer MSVD-QA Elysium Confidence Score 3.7 #10 of 28 Archive leaderboard report
Zero-Shot Video Question Answer TGIF-QA Elysium Accuracy 66.6 #11 of 14 Archive leaderboard report
Zero-Shot Video Question Answer TGIF-QA Elysium Confidence Score 3.6 #11 of 14 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.

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