Andrew Zisserman

15

Papers

96

Total Citations

Papers (15)

A Simple Recipe for Contrastively Pre-training Video-First Encoders Beyond 16 Frames

AutoAD III: The Prequel – Back to the Pixels

Learning from One Continuous Video Stream

Made to Order: Discovering monotonic temporal changes via self-supervised video ordering

From Panels to Prose: Generating Literary Narratives from Comics

Shot-by-Shot: Film-Grammar-Aware Training-Free Audio Description Generation

Amodal Ground Truth and Completion in the Wild

The Manga Whisperer: Automatically Generating Transcriptions for Comics

Lost in Translation, Found in Context: Sign Language Translation with Contextual Cues

TIM: A Time Interval Machine for Audio-Visual Action Recognition

Learning from Streaming Video with Orthogonal Gradients

LayerLock: Non-collapsing Representation Learning with Progressive Freezing

Understanding Co-speech Gestures in-the-wild

SciVid: Cross-Domain Evaluation of Video Models in Scientific Applications

Separating the "Chirp" from the "Chat": Self-supervised Visual Grounding of Sound and Language