147 citations · 150 across the 4 of their papers we have counts for
4 papers · 1 filter
VLRM: Vision-Language Models act as Reward Models for Image Captioning
Maksim Dzabraev, Alexander Kunitsyn, Andrei Ivaniuta
In this work, we present an unsupervised method for enhancing an image captioning model (in our case, BLIP2) using reinforcement learning and vision-language models like CLIP and B…
MDMMT-2: Multidomain Multimodal Transformer for Video Retrieval, One More Step Towards Generalization
Alexander Kunitsyn, Maksim Kalashnikov, Maksim Dzabraev +1
In this work we present a new State-of-The-Art on the text-to-video retrieval task on MSR-VTT, LSMDC, MSVD, YouCook2 and TGIF obtained by a single model. Three different data sourc…
MDMMT: Multidomain Multimodal Transformer for Video Retrieval
Maksim Dzabraev, Maksim Kalashnikov, Stepan Komkov +1
We present a new state-of-the-art on the text to video retrieval task on MSRVTT and LSMDC benchmarks where our model outperforms all previous solutions by a large margin. Moreover,…
Mutual Modality Learning for Video Action Classification
Stepan Komkov, Maksim Dzabraev, Aleksandr Petiushko
The construction of models for video action classification progresses rapidly. However, the performance of those models can still be easily improved by ensembling with the same mod…