Pith. sign in

REVIEW 4 cited by

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

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2207.00383 v2 pith:GCIJPJ2U submitted 2022-07-01 cs.CV cs.IR

Naiyuan Liu , Xiaohan Wang , Xiaobo Li , Yi Yang , Yueting Zhuang This is my paper · ORCID
classification cs.CVcs.IR
keywords videochallengelanguagequeriessubmissionclipego4dnatural
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

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.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 4 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. ReVisionLLM: Recursive Vision-Language Model for Temporal Grounding in Hour-Long Videos

    cs.CV 2024-11 conditional novelty 7.0 of 10

    A recursive vision-language model with sparse and dense video features reports state-of-the-art temporal grounding on hour-long videos.

  2. Object-Shot Enhanced Grounding Network for Egocentric Video

    cs.CV 2025-05 accept novelty 6.0 of 10

    OSGNet uses query-relevant object features from a detector and contrastive shot learning from head-movement captions to achieve state-of-the-art egocentric video grounding.

  3. Online Episodic Memory Visual Query Localization with Egocentric Streaming Object Memory

    cs.CV 2024-11 conditional novelty 6.0 of 10

    The paper defines the online episodic-memory query task OVQ2D and shows ESOM, a detect-track-memorize-retrieve system, achieves only ~4% success on Ego4D, rising to 81.92% with oracle detection and tracking.

  4. GazeNLQ @ Ego4D Natural Language Queries Challenge 2025

    cs.CV 2025-06 conditional novelty 5.0 of 10

    GazeNLQ adds contrastively pretrained gaze embeddings to a GroundNLQ-style grounding model, reporting 27.82 R1@0.3 on the Ego4D NLQ test split only when ensembled with GroundVQA.

Pith tools