Methods › Sequential › Bidirectional Recurrent Neural Networks › U-RNNs

Asymmetrical Bi-RNN

U-RNNs

2 papers tagged archive 2025-07-28

Introduced by Raphaël Rozenberg et al. in Asymmetrical Bi-RNN for pedestrian trajectory encoding

archive 2025-07-28 Description, source and code snippet are the archive's method entry.

An aspect of Bi-RNNs that could be undesirable is the architecture's symmetry in both time directions.

Bi-RNNs are often used in natural language processing, where the order of the words is almost exclusively determined by grammatical rules and not by temporal sequentiality. However, in some cases, the data has a preferred direction in time: the forward direction.

Another potential drawback of Bi-RNNs is that their output is simply the concatenation of two naive readings of the input in both directions. In consequence, Bi-RNNs never actually read an input by knowing what happens in the future. Conversely, the idea behind U-RNN, is to first do a backward pass, and then use during the forward pass information about the future.

We accumulate information while knowing which part of the information will be useful in the future as it should be relevant to do so if the forward direction is the preferred direction of the data.

The backward and forward hidden states (hᵇₜ) and (hᶠₜ) are obtained according to these equations:

hₜ₋₁ᵇ=R N N(hₜᵇ, eₜ, W_b) hₜ₊₁ᶠ=R N N(hₜᶠ,[eₜ, hₜᵇ], W_f)

where W_b and W_f are learnable weights that are shared among pedestrians, and [·, ·] denotes concatenation. The last hidden state hᶠ_(T_(obs)) is then used as the encoding of the sequence.

PaperSourceSee Code · JosephGesnouin/Asymmetrical-Bi-RNNs-to-encode-pedestrian-trajectories

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: Banded RNNs; Selective-Update RNNs; Structural Evolution RNNs (SE-RNNs); Almost-Linear Recurrent Neural Networks (AL-RNNs); physics-constrained RNNs for temperature nowcasting.

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: 2 · with a code link: 1 · 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 2 tagged papers has a Syntology run on record

Page 1 of 1: papers 1 to 2 of 2, 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.

Tasks archive 2025-07-28

5 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.

TaskPapers
Autonomous Driving1
Autonomous Navigation1
Pedestrian Trajectory Prediction1
Trajectory Forecasting1
Trajectory Prediction1

Usage over time archive 2025-07-28

Papers per year tagged with U-RNNs: 2021 to 2021, peak 2 2 0 2021: 2 papers 2021
Papers per year the archive tags with this method, by the paper's archive date (2 dated). Bars are counts, not a trend claim.

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

Bidirectional Recurrent Neural Networks

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