Papers › Where to put the Image in an Image Caption Generator

Where to put the Image in an Image Caption Generator

27 Mar 2017arXiv:1703.09137archive 2025-07-28

Marc Tanti, Albert Gatt, Kenneth P. Camilleri

When a recurrent neural network language model is used for caption generation, the image information can be fed to the neural network either by directly incorporating it in the RNN -- conditioning the language model by `injecting' image features -- or in a layer following the RNN -- conditioning the language model by `merging' image features. While both options are attested in the literature, there is as yet no systematic comparison between the two. In this paper we empirically show that it is not especially detrimental to performance whether one architecture is used or another. The merge architecture does have practical advantages, as conditioning by merging allows the RNN's hidden state vector to shrink in size by up to four times. Our results suggest that the visual and linguistic modalities for caption generation need not be jointly encoded by the RNN as that yields large, memory-intensive models with few tangible advantages in performance; rather, the multimodal integration should be delayed to a subsequent stage.

PaperPDFCode

Code

bmy4415/DMLAB-intern mentioned on GitHubtf report
kahotsang/image-captioning mentioned on GitHubtf report
mtanti/rnn-role mentioned on GitHubtf report
nicolafan/image-captioning-cnn-rnn mentioned on GitHubtfMIT report
thomasvengal/deeplearning mentioned on GitHubtf 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

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

Tasks

Caption GenerationLanguage ModelingLanguage Modelling

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

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