English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Tools annual

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Recognizing objects from sparse and noisy events becomes extremely difficultwhen paired images and category labels do not exist. In this paper, we studylabel-free event-based object recognition where category labels and pairedimages are not available. To this end, we propose a joint formulation of objectrecognition and image reconstruction in a complementary manner. Our methodfirst reconstructs images from events and performs object recognition throughContrastive Language-Image Pre-training (CLIP), enabling better recognitionthrough a rich context of images. Since the category information is essentialin reconstructing images, we propose category-guided attraction loss andcategory-agnostic repulsion loss to bridge the textual features of predictedcategories and the visual features of reconstructed images using CLIP.Moreover, we introduce a reliable data sampling strategy and local-globalreconstruction consistency to boost joint learning of two tasks. To enhance theaccuracy of prediction and quality of reconstruction, we also propose aprototype-based approach using unpaired images. Extensive experimentsdemonstrate the superiority of our method and its extensibility for zero-shotobject recognition. Our project code is available at\url{https://github.com/Chohoonhee/Ev-LaFOR}.

Label-Free Event-based Object Recognition via Joint Learning with Image Reconstruction from Events