Pith. sign in

REVIEW 2 cited by

Event Transformer

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2204.05172 v2 pith:E3VF2NXP submitted 2022-04-11 cs.CV

classification cs.CV
keywords eventrepresentationdeviceseventsmethodsprocessingtemporaltoken-based
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

The event camera's low power consumption and ability to capture microsecond brightness changes make it attractive for various computer vision tasks. Existing event representation methods typically convert events into frames, voxel grids, or spikes for deep neural networks (DNNs). However, these approaches often sacrifice temporal granularity or require specialized devices for processing. This work introduces a novel token-based event representation, where each event is considered a fundamental processing unit termed an event-token. This approach preserves the sequence's intricate spatiotemporal attributes at the event level. Moreover, we propose a Three-way Attention mechanism in the Event Transformer Block (ETB) to collaboratively construct temporal and spatial correlations between events. We compare our proposed token-based event representation extensively with other prevalent methods for object classification and optical flow estimation. The experimental results showcase its competitive performance while demanding minimal computational resources on standard devices. Our code is publicly accessible at \url{https://github.com/NJUVISION/EventTransformer}.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 2 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. DELTA: Dense Depth from Events and LiDAR using Transformer's Attention

    cs.CV 2025-05 conditional novelty 6.0 of 10

    DELTA fuses event camera and LiDAR data with transformer attention and recurrent memory to estimate dense depth maps, reporting large close-range error reductions over prior work.

  2. Static in Frames, Dynamic in Events: Rethinking Features in Event Cameras as Motion Cues

    cs.CV 2026-08 conditional novelty 5.0 of 10

    Harris eigenvalues and spatiotemporal density values from event cameras encode motion direction and, when added to an optical flow network, improve accuracy in data-scarce settings.

Pith tools