</> Code with Papers by Syntology

Papers › SEM-POS: Grammatically and Semantically Correct Video Captioning

SEM-POS: Grammatically and Semantically Correct Video Captioning

26 Mar 2023arXiv:2303.14829archive 2025-07-28

Asmar Nadeem, Adrian Hilton, Robert Dawes, Graham Thomas, Armin Mustafa

Generating grammatically and semantically correct captions in video captioning is a challenging task. The captions generated from the existing methods are either word-by-word that do not align with grammatical structure or miss key information from the input videos. To address these issues, we introduce a novel global-local fusion network, with a Global-Local Fusion Block (GLFB) that encodes and fuses features from different parts of speech (POS) components with visual-spatial features. We use novel combinations of different POS components - 'determinant + subject', 'auxiliary verb', 'verb', and 'determinant + object' for supervision of the POS blocks - Det + Subject, Aux Verb, Verb, and Det + Object respectively. The novel global-local fusion network together with POS blocks helps align the visual features with language description to generate grammatically and semantically correct captions. Extensive qualitative and quantitative experiments on benchmark MSVD and MSRVTT datasets demonstrate that the proposed approach generates more grammatically and semantically correct captions compared to the existing methods, achieving the new state-of-the-art. Ablations on the POS blocks and the GLFB demonstrate the impact of the contributions on the proposed method.

PaperPDF

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

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

POSVideo Captioning

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Video Captioning MSR-VTT SEM-POS BLEU-4 45.2 #23 of 24 Archive leaderboard report
Video Captioning MSR-VTT SEM-POS CIDEr 53.1 #23 of 24 Archive leaderboard report
Video Captioning MSR-VTT SEM-POS GS 192.6 #23 of 24 Archive leaderboard report
Video Captioning MSR-VTT SEM-POS METEOR 30.7 #23 of 24 Archive leaderboard report
Video Captioning MSR-VTT SEM-POS ROUGE-L 64.1 #23 of 24 Archive leaderboard report
Video Captioning MSRVTT-CTN SEM-POS CIDEr 26.01 #3 of 4 Archive leaderboard report
Video Captioning MSRVTT-CTN SEM-POS ROUGE-L 20.11 #3 of 4 Archive leaderboard report
Video Captioning MSRVTT-CTN SEM-POS SPICE 12.09 #3 of 4 Archive leaderboard report
Video Captioning MSVD SEM-POS BLEU-4 60.1 #14 of 16 Archive leaderboard report
Video Captioning MSVD SEM-POS CIDEr 108.3 #14 of 16 Archive leaderboard report
Video Captioning MSVD SEM-POS GS 607.1 #14 of 16 Archive leaderboard report
Video Captioning MSVD SEM-POS METEOR 38.5 #14 of 16 Archive leaderboard report
Video Captioning MSVD SEM-POS ROUGE-L 76.0 #14 of 16 Archive leaderboard report
Video Captioning MSVD-CTN SEM-POS CIDEr 37.16 #3 of 4 Archive leaderboard report
Video Captioning MSVD-CTN SEM-POS ROUGE-L 25.39 #3 of 4 Archive leaderboard report
Video Captioning MSVD-CTN SEM-POS SPICE 14.46 #3 of 4 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

ALIGN

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