Methods › General › Attention Mechanisms › Bi-attention
Bilinear Attention
Bi-attention
Introduced by Pengfei Fang et al. in Bilinear Attention Networks for Person Retrieval
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
Bi-attention employs the attention-in-attention (AiA) mechanism to capture second-order statistical information: the outer point-wise channel attention vectors are computed from the output of the inner channel attention.
In Syntology name not resolved (unknown_name). The lookup matched no method, paper or venue by this name; that asserts nothing about whether code exists.
Near matches the lookup lists, each a different name: attention-based BiLSTM; Attention-Based BiLSTM; Probabilistic Attention; Active Attention Probing; power law attention biases; bi-level routing attention; Cross-Modal Binary Attention; Soft-Target Attention Probing.
Syntology's have check for this name (free, it answers coverage only), read 2026-10-05; ask it again live. A level is the served verification level of that one answer; nothing here is summed across methods.
Papers archive 2025-07-28
archive papers tagged: 11 · with a code link: 4 · where Syntology ran a sample: 0 (0 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran: none of the 11 tagged papers has a Syntology run on record
Page 1 of 1: papers 1 to 11 of 11, newest first by the archive's date (ties by slug), in archive order.
Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code, as “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. It is per sample and not a correctness claim. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from.
-
DiaMond: Dementia Diagnosis with Multi-Modal Vision Transformers Using MRI and PET 30 Oct 2024 · 1 repository · arXiv:2410.23219
-
Elite360M: Efficient 360 Multi-task Learning via Bi-projection Fusion and Cross-task Collaboration 18 Aug 2024 · 0 repositories · arXiv:2408.09336
-
Elite360D: Towards Efficient 360 Depth Estimation via Semantic- and Distance-Aware Bi-Projection Fusion 25 Mar 2024 · 0 repositories · arXiv:2403.16376
-
Alzheimer's Disease Prediction via Brain Structural-Functional Deep Fusing Network 28 Sep 2023 · 0 repositories · arXiv:2309.16206
-
GraphCare: Enhancing Healthcare Predictions with Personalized Knowledge Graphs 22 May 2023 · 0 repositories · arXiv:2305.12788
-
Tri-Attention: Explicit Context-Aware Attention Mechanism for Natural Language Processing 5 Nov 2022 · 1 repository · arXiv:2211.02899
-
Cross-Modal Transformer GAN: A Brain Structure-Function Deep Fusing Framework for Alzheimer's Disease 20 Jun 2022 · 0 repositories · arXiv:2206.13393
-
Compare learning: bi-attention network for few-shot learning 25 Mar 2022 · 0 repositories · arXiv:2203.13487
-
BiBERT: Accurate Fully Binarized BERT 12 Mar 2022 · 1 repository · arXiv:2203.06390
-
Gated Convolutional Bidirectional Attention-based Model for Off-topic Spoken Response Detection 20 Apr 2020 · 1 repository · arXiv:2004.09036
-
Bilinear Attention Networks for Person Retrieval 1 Oct 2019 · 0 repositories
Tasks archive 2025-07-28
20 shown of 21 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.
| Task | Papers |
|---|---|
| ERP | 2 |
| Generative Adversarial Network | 2 |
| 3D Reconstruction | 1 |
| 3D geometry | 1 |
| Binarization | 1 |
| Decision Making | 1 |
| Depth Estimation | 1 |
| Disease Prediction | 1 |
| Few-Shot Learning | 1 |
| Graph Neural Network | 1 |
| Knowledge Graphs | 1 |
| Machine Reading Comprehension | 1 |
| Metric Learning | 1 |
| Multi-Task Learning | 1 |
| Person Retrieval | 1 |
| Question Answering | 1 |
| Retrieval | 1 |
| Semantic Segmentation | 1 |
| Sentence | 1 |
| Surface Normal Estimation | 1 |
Usage over time archive 2025-07-28
Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).
Categories archive 2025-07-28
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