UniUD Submission to the EPIC-Kitchens-100 Multi-Instance Retrieval Challenge 2023

Alex Falcon; Giuseppe Serra

RECORD

UniUD Submission to the EPIC-Kitchens-100 Multi-Instance Retrieval Challenge 2023

Alex Falcon, Giuseppe Serra

Computer Vision and Pattern Recognition · Submitted 27 Jun 2023

abstract compiled · 2026-09-23 · no language-model review

The authors' main claim Our submission, visible on the public leaderboard, obtains an average score of 56.81% nDCG and 42.63% mAP.

how it is stated · asserted 1.00 read the record →

Comment (0) Read on arXiv ↗

Cite ▾

arXiv ID2306.15445 (version 2)

Pith IDC2KW6OXA, Pith's permanent record of this paper and its review

CitationAlex Falcon, Giuseppe Serra. "UniUD Submission to the EPIC-Kitchens-100 Multi-Instance Retrieval Challenge 2023." arXiv:2306.15445 (2023). https://pith.science/paper/C2KW6OXA

Claim paper

The compiled record

The paper's own sentences, arranged. Each label is drawn from a closed vocabulary; the number beside it is the probability the classifier gave that label. Numbers in the tables are the authors', checked by code. No sentence in this record was written by a model.

Open the compiled record

Compiled by classifier-1.13.0 via TypeSafe API, question bank abstract-p1-20260923, 2026-09-23: 1 request, 2,974 input tokens.

What the abstract itself states, as probabilities: claims first 0.02 · states limitation 0.17 · human participants 0.06 · controlled comparison 0.04 · randomized assignment 0.02 · states quantitative result 0.99 · compares with prior results 0.06 · mentions code or data availability 0.12.

The abstract, sentence by sentence

arXiv listing abstract v2. Results and the main claim are underlined; show every role.

In this report, we present the technical details of our submission to the EPIC-Kitchens-100 Multi-Instance Retrieval Challenge 2023. To participate in the challenge, we ensembled two models trained with two different loss functions on 25% of the training data. Our submission, visible on the public leaderboard, obtains an average score of 56.81% nDCG and 42.63% mAP.

background contribution method result interpretation main claim

What the classifier reports for each sentence. The number is the probability it gave the label.
#	sentence	role	the authors' own work	states the main conclusion	strength
s0	In this report, we present the technical details of our submission to the EPIC-Kitchens-100 Multi-Instance Retrieval Challenge 2023.	contribution 0.97	0.84	0.07	asserted 0.95
s1	To participate in the challenge, we ensembled two models trained with two different loss functions on 25% of the training data.	method 1.00	0.95	0.06	asserted 1.00
s2	Our submission, visible on the public leaderboard, obtains an average score of 56.81% nDCG and 42.63% mAP.	result 1.00	0.97	0.60	asserted 1.00

What kind of paper the classifier reports this is: method or tool 0.67 · evidence from observation or experiment 0.78.

What was examined, and what was not

sources read

arXiv listing abstract v2

not examined

full text
figures and tables
references and citing sentences
relations to other papers

levels run

P abstract

not run

S sections
T body sentences
C citations
R cross-paper relations

Every quoted sentence on this record is the authors'. Every label is from Pith's closed vocabulary, with the probability shown beside it. Every number in the measurements table is the authors', checked by code. Record as JSON

The paper

Original abstract

In this report, we present the technical details of our submission to the EPIC-Kitchens-100 Multi-Instance Retrieval Challenge 2023. To participate in the challenge, we ensembled two models trained with two different loss functions on 25% of the training data. Our submission, visible on the public leaderboard, obtains an average score of 56.81% nDCG and 42.63% mAP.

Human review

How Pith checks papers → · Full audit of this paper →

How the literature uses it

What this paper does with the arXiv papers it cites

Each citing sentence is taken from the citing paper's LaTeX source and typed by Pith's classifier. A label appears at probability 0.8 or more (0.95 for support), a contest at 0.7 or more; the quoted words are the citing authors'. How each label was checked · JSON

What it cites · 1 sentence without a confident label

Uses the method or tool of 2 papers

The first method included in our final solution uses a data augmentation technique on top of RANP [ref] , whereas the second one is a novel approach based on direct nDCG optimization [ref] .

NeuralNDCG: Direct Optimisation of a Ranking Metric via Differentiable Relaxation of Sorting · Introduction · 1.00
We deployed a simple ensemble strategy based on last year's submission [ref] .

UniUD-FBK-UB-UniBZ Submission to the EPIC-Kitchens-100 Multi-Instance Retrieval Challenge 2022 · Ensemble strategy · 0.92

Compares with 3 papers

When compared to the 2021 and 2022 editions of the EPIC-Kitchens-100 Multi-Instance Retrieval Challenge 2021 [ref] , we observe a better nDCG (+1.5%) with similar mAP (only -0.2%) than Satar et al.'s submission which obtained 55.33% nDCG and 42.81% mAP on average [ref] , and +3.3% nDCG compared to the official JPoSE baseline and Hao et al.'s submission at the price of 1.4% mAP [ref] .

Exploiting Semantic Role Contextualized Video Features for Multi-Instance Text-Video Retrieval EPIC-KITCHENS-100 Multi-Instance Retrieval Challenge 2022 · Results · 0.99
With respect to last year winners, Lin et al. and our previous submission [ref] , we obtain a good nDCG (around 4% less) but the mAP is still far from optimal (around 7% less than [ref] ).

UniUD-FBK-UB-UniBZ Submission to the EPIC-Kitchens-100 Multi-Instance Retrieval Challenge 2022 · Results · 1.00
With respect to last year winners, Lin et al. and our previous submission [ref] , we obtain a good nDCG (around 4% less) but the mAP is still far from optimal (around 7% less than [ref] ).

Egocentric Video-Language Pretraining @ EPIC-KITCHENS-100 Multi-Instance Retrieval Challenge 2022 · Results · 1.00

Discussion

Know something about this paper? Leave a comment, or highlight any passage above to comment on it.