Image difference captioning with instance-level fine-grained feature representation
The task of image difference captioning aims at locating changed objects in similar image
pairs and describing the difference with natural language. The key challenges of this task …
pairs and describing the difference with natural language. The key challenges of this task …
Memory-augmented image captioning
Z Fei - Proceedings of the AAAI Conference on Artificial …, 2021 - ojs.aaai.org
Current deep learning-based image captioning systems have been proven to store practical
knowledge with their parameters and achieve competitive performances in the public …
knowledge with their parameters and achieve competitive performances in the public …
Partially non-autoregressive image captioning
Z Fei - Proceedings of the AAAI Conference on Artificial …, 2021 - ojs.aaai.org
Current state-of-the-art image captioning systems usually generated descriptions
autoregressively, ie, every forward step conditions on the given image and previously …
autoregressively, ie, every forward step conditions on the given image and previously …
Efficient modeling of future context for image captioning
Z Fei - Proceedings of the 30th ACM International Conference …, 2022 - dl.acm.org
Existing approaches to image captioning usually generate the sentence word-by-word from
left to right, with the constraint of conditioned on local context including the given image and …
left to right, with the constraint of conditioned on local context including the given image and …
Iterative back modification for faster image captioning
Z Fei - Proceedings of the 28th ACM international conference …, 2020 - dl.acm.org
Current state-of-the-art image captioning systems generally produce a sentence from left to
right, and every step is conditioned on the given image and previously generated words …
right, and every step is conditioned on the given image and previously generated words …
Scene graph with 3D information for change captioning
Change captioning aims to describe the differences in image pairs with natural language. It
is an interesting task under-explored with two main challenges: describing the relative …
is an interesting task under-explored with two main challenges: describing the relative …
Self-Training Boosted Multi-Factor Matching Network for Composed Image Retrieval
The composed image retrieval (CIR) task aims to retrieve the desired target image for a
given multimodal query, ie, a reference image with its corresponding modification text. The …
given multimodal query, ie, a reference image with its corresponding modification text. The …
Retrieve and revise: improving peptide identification with similar mass spectra
Z Fei - Proceedings of the AAAI Conference on Artificial …, 2021 - ojs.aaai.org
Tandem mass spectrometry is an indispensable technology for identification of proteins from
complex mixtures. Accurate and sensitive analysis of large amounts of mass spectra data is …
complex mixtures. Accurate and sensitive analysis of large amounts of mass spectra data is …