Papers › ReLER@ZJU-Alibaba Submission to the Ego4D Natural Language Queries Challenge 2022

ReLER@ZJU-Alibaba Submission to the Ego4D Natural Language Queries Challenge 2022

1 Jul 2022arXiv:2207.00383archive 2025-07-28

Naiyuan Liu, Xiaohan Wang, Xiaobo Li, Yi Yang, Yueting Zhuang

In this report, we present the ReLER@ZJU-Alibaba submission to the Ego4D Natural Language Queries (NLQ) Challenge in CVPR 2022. Given a video clip and a text query, the goal of this challenge is to locate a temporal moment of the video clip where the answer to the query can be obtained. To tackle this task, we propose a multi-scale cross-modal transformer and a video frame-level contrastive loss to fully uncover the correlation between language queries and video clips. Besides, we propose two data augmentation strategies to increase the diversity of training samples. The experimental results demonstrate the effectiveness of our method. The final submission ranked first on the leaderboard.

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="2207.00383")

Code

Syntology Ran 6 of 19 code samples harvested from 1 repository linked to this paper; 13 have no recorded run. Of those that ran: 3 ran · honoured contract; 1 ran · our draft was wrong; 2 ran with no contract checked.

By repository: official repository: 19 samples from 1 repository, 6 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

nnnnai/ego4d_nlq_2022_1st_place_solution officialmentioned in papermentioned on GitHubpytorchMIT 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

19 samples harvested; 6 ran; 3 honoured the contract we drafted; 13 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

3ran · honoured contract
1ran · our draft was wrong
2ran
13unverified

Licence: 0 of the 19 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 nnnnai/ego4d_nlq_2022_1st_place_solution. “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.

swish nnnnai/ego4d_nlq_2022_1st_place_solution/ms_cm/bert_layers.py official repository ran · our draft was wrong fingerprinted MIT (permissive) · 0f786c407fb1ee4c · report
gelu nnnnai/ego4d_nlq_2022_1st_place_solution/ms_cm/bert_layers.py official repository ran · honoured contract fingerprinted MIT (permissive) · c2f0705ed8e6f7e6 · report
index_to_time nnnnai/ego4d_nlq_2022_1st_place_solution/ms_cm/inference_ego4d_slowfast.py official repository ran · honoured contract MIT (permissive) · 5afa136a77ba325a · report
load_json nnnnai/ego4d_nlq_2022_1st_place_solution/ms_cm/vslnet_utils.py official repository ran MIT (permissive) · a8ccf61e0ee23809 · report
load_pickle nnnnai/ego4d_nlq_2022_1st_place_solution/ms_cm/vslnet_utils.py official repository ran MIT (permissive) · 259b0af842be3b00 · report
mask_logits nnnnai/ego4d_nlq_2022_1st_place_solution/ms_cm/model.py official repository ran · honoured contract fingerprinted MIT (permissive) · 60df4d5a1eee1b92 · report
compute_IoU nnnnai/ego4d_nlq_2022_1st_place_solution/ms_cm/vslnet_utils/evaluate_ego4d_nlq.py official repository unverified MIT (permissive) · b504027a68e6008e · report
count_parameters nnnnai/ego4d_nlq_2022_1st_place_solution/utils/model_utils.py official repository unverified MIT (permissive) · edb929dece68582e · report
extract_index nnnnai/ego4d_nlq_2022_1st_place_solution/ms_cm/train_ego4d_slowfast.py official repository unverified MIT (permissive) · 27d5aa25eb321b6b · report
filter_glove_embedding nnnnai/ego4d_nlq_2022_1st_place_solution/ms_cm/vslnet_utils/data_gen_ego4d.py official repository unverified MIT (permissive) · 094900ebac5a22d2 · report
get_nearest_frame nnnnai/ego4d_nlq_2022_1st_place_solution/ms_cm/vslnet_utils/prepare_ego4d_dataset.py official repository unverified MIT (permissive) · 8981315bccaefd02 · report
load_glove nnnnai/ego4d_nlq_2022_1st_place_solution/ms_cm/vslnet_utils/data_gen_ego4d.py official repository unverified MIT (permissive) · 623b22c7208a83a3 · report
load_lines nnnnai/ego4d_nlq_2022_1st_place_solution/ms_cm/vslnet_utils.py official repository unverified MIT (permissive) · f319d88d5afe29f2 · report
pad_text_tenor_list nnnnai/ego4d_nlq_2022_1st_place_solution/ms_cm/model.py official repository unverified MIT (permissive) · 1407d4bc17dab94d · report
prepare_batch_inputs nnnnai/ego4d_nlq_2022_1st_place_solution/ms_cm/sw_vs_ego4d_dataset.py official repository unverified MIT (permissive) · fede2bee168d55fb · report
process_question nnnnai/ego4d_nlq_2022_1st_place_solution/ms_cm/vslnet_utils/prepare_ego4d_dataset.py official repository unverified MIT (permissive) · eff6500b503388a1 · report
reformat_data nnnnai/ego4d_nlq_2022_1st_place_solution/ms_cm/vslnet_utils/prepare_ego4d_dataset.py official repository unverified MIT (permissive) · 2b49f220ea389d78 · report
visual_feature_sampling nnnnai/ego4d_nlq_2022_1st_place_solution/ms_cm/sw_vs_ego4d_dataset.py official repository unverified MIT (permissive) · be98c34a85ec275b · report
vocab_emb_gen nnnnai/ego4d_nlq_2022_1st_place_solution/ms_cm/vslnet_utils/data_gen_ego4d.py official repository unverified MIT (permissive) · 76e886ecae69991a · report

Tasks

Data AugmentationDiversityNatural Language Queries

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Natural Language Queries Ego4D ReLER@ZJU-Alibaba R@1 IoU=0.3 12.89 #8 of 10 Archive leaderboard report
Natural Language Queries Ego4D ReLER@ZJU-Alibaba R@1 IoU=0.5 8.14 #8 of 10 Archive leaderboard report
Natural Language Queries Ego4D ReLER@ZJU-Alibaba R@1 Mean(0.3 and 0.5) 10.52 #8 of 10 Archive leaderboard report
Natural Language Queries Ego4D ReLER@ZJU-Alibaba R@5 IoU=0.3 15.41 #8 of 10 Archive leaderboard report
Natural Language Queries Ego4D ReLER@ZJU-Alibaba R@5 IoU=0.5 9.94 #8 of 10 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

CLIP

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