Feature Hallucination for Self-supervised Action Recognition
–arXiv.org Artificial Intelligence
Understanding human actions in videos requires more than raw pixel analysis; it relies on high-level semantic reasoning and effective integration of multimodal features. We propose a deep translational action recognition framework that enhances recognition accuracy by jointly predicting action concepts and auxiliary features from RGB video frames. At test time, hallucination streams infer missing cues, enriching feature representations without increasing computational overhead. To focus on action-relevant regions beyond raw pixels, we introduce two novel domain-specific descriptors. Object Detection Features (ODF) aggregate outputs from multiple object detectors to capture contextual cues, while Saliency Detection Features (SDF) highlight spatial and intensity patterns crucial for action recognition. Our framework seamlessly integrates these descriptors with auxiliary modalities such as optical flow, Improved Dense Trajectories, skeleton data, and audio cues. It remains compatible with state-of-the-art architectures, including I3D, AssembleNet, Video Transformer Network, FASTER, and recent models like VideoMAE V2 and InternVideo2. To handle uncertainty in auxiliary features, we incorporate aleatoric uncertainty modeling in the hallucination step and introduce a robust loss function to mitigate feature noise. Our multimodal self-supervised action recognition framework achieves state-of-the-art performance on multiple benchmarks, including Kinetics-400, Kinetics-600, and Something-Something V2, demonstrating its effectiveness in capturing fine-grained action dynamics.
arXiv.org Artificial Intelligence
Jun-26-2025
- Country:
- Africa > Ethiopia
- Addis Ababa > Addis Ababa (0.04)
- Asia
- China (0.04)
- Macao (0.04)
- South Korea > Seoul
- Seoul (0.04)
- Europe
- Czechia > Prague (0.04)
- Belgium > Brussels-Capital Region
- Brussels (0.04)
- Spain > Catalonia
- Barcelona Province > Barcelona (0.04)
- Italy (0.04)
- United Kingdom > England
- West Yorkshire > Leeds (0.04)
- Netherlands
- North Holland > Amsterdam (0.04)
- South Holland > Dordrecht (0.04)
- France > Provence-Alpes-Côte d'Azur
- Alpes-Maritimes > Nice (0.04)
- Bouches-du-Rhône > Marseille (0.04)
- Germany > Bavaria
- Upper Bavaria > Munich (0.04)
- Austria > Styria
- Graz (0.04)
- North America
- Canada
- Alberta > Census Division No. 15
- Improvement District No. 9 > Banff (0.04)
- Quebec > Montreal (0.04)
- Alberta > Census Division No. 15
- Puerto Rico > San Juan
- San Juan (0.04)
- United States
- California
- Los Angeles County > Long Beach (0.04)
- San Francisco County > San Francisco (0.14)
- Sonoma County > Santa Rosa (0.04)
- Massachusetts
- Middlesex County > Cambridge (0.04)
- Suffolk County > Boston (0.04)
- Colorado > El Paso County
- Colorado Springs (0.04)
- Florida > Palm Beach County
- Boca Raton (0.04)
- Washington > King County
- Seattle (0.04)
- Illinois > Cook County
- Chicago (0.04)
- Utah > Salt Lake County
- Salt Lake City (0.04)
- Rhode Island > Providence County
- Providence (0.04)
- Hawaii > Honolulu County
- Honolulu (0.04)
- Ohio > Franklin County
- Columbus (0.04)
- Minnesota > Hennepin County
- Minneapolis (0.14)
- California
- Canada
- Oceania > Australia
- New South Wales > Sydney (0.14)
- Western Australia (0.04)
- South America > Chile
- Africa > Ethiopia
- Genre:
- Overview (0.92)
- Research Report > New Finding (0.46)
- Industry:
- Automobiles & Trucks (0.93)
- Technology: