Hartwig Adam

29

Papers

138

Total Citations

Papers (29)

Naive-Student: Leveraging Semi-Supervised Learning in Video Sequences for Urban Scene Segmentation

Distilling Vision-Language Models on Millions of Videos

VideoPrism: A Foundational Visual Encoder for Video Understanding

BranchOut: Regularization for Online Ensemble Tracking With Convolutional Neural Networks

Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference

MaskLab: Instance Segmentation by Refining Object Detection With Semantic and Direction Features

The INaturalist Species Classification and Detection Dataset

Auto-DeepLab: Hierarchical Neural Architecture Search for Semantic Image Segmentation

FEELVOS: Fast End-To-End Embedding Learning for Video Object Segmentation

Panoptic-DeepLab: A Simple, Strong, and Fast Baseline for Bottom-Up Panoptic Segmentation

MnasFPN: Learning Latency-Aware Pyramid Architecture for Object Detection on Mobile Devices

VIP-DeepLab: Learning Visual Perception With Depth-Aware Video Panoptic Segmentation

Learning View-Disentangled Human Pose Representation by Contrastive Cross-View Mutual Information Maximization

MaX-DeepLab: End-to-End Panoptic Segmentation With Mask Transformers

CMT-DeepLab: Clustering Mask Transformers for Panoptic Segmentation

TubeFormer-DeepLab: Video Mask Transformer

Improving Zero-Shot Generalization and Robustness of Multi-Modal Models

Searching for MobileNetV3

Unified Visual Relationship Detection with Vision and Language Models

Fashionpedia: Ontology, Segmentation, and an Attribute Localization Dataset

Axial-DeepLab: Stand-Alone Axial-Attention for Panoptic Segmentation

View-Invariant Probabilistic Embedding for Human Pose

Exploring Fine-Grained Audiovisual Categorization with the SSW60 Dataset

Adaptive Transformers for Robust Few-Shot Cross-Domain Face Anti-Spoofing

k-Means Mask Transformer

Contextualized Spatio-Temporal Contrastive Learning With Self-Supervision

VideoPoet: A Large Language Model for Zero-Shot Video Generation

Searching for Efficient Multi-Scale Architectures for Dense Image Prediction

Alternating Gradient Descent and Mixture-of-Experts for Integrated Multimodal Perception