DACG-IR adds a lightweight degradation-aware module that generates prompts to adaptively gate attention temperature, output features, and spatial-channel fusion in an encoder-decoder network for unified image restoration.
Object detection in 20 years: A survey
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
years
2026 4verdicts
UNVERDICTED 4representative citing papers
PASTA enables patch-agnostic backdoor activation in ViTs via multi-location trigger insertion during training and bi-level optimization, achieving 99.13% average attack success with large gains in visual/attention stealthiness and defense robustness.
VLMaterial fuses VLMs and physics-based radar analysis via PRCA extraction and context-augmented generation to reach 96.08% material identification accuracy on 41 everyday objects without task-specific training.
Raw proximity measurements can substitute for explicit object localization in humanoid collision avoidance if sensing range is sufficient, and sparse non-directional proximity signals train more efficiently than dense directional alternatives.
citing papers explorer
-
Degradation-Aware Adaptive Context Gating for Unified Image Restoration
DACG-IR adds a lightweight degradation-aware module that generates prompts to adaptively gate attention temperature, output features, and spatial-channel fusion in an encoder-decoder network for unified image restoration.
-
PASTA: A Patch-Agnostic Twofold-Stealthy Backdoor Attack on Vision Transformers
PASTA enables patch-agnostic backdoor activation in ViTs via multi-location trigger insertion during training and bi-level optimization, achieving 99.13% average attack success with large gains in visual/attention stealthiness and defense robustness.
-
VLMaterial: Vision-Language Model-Based Camera-Radar Fusion for Physics-Grounded Material Identification
VLMaterial fuses VLMs and physics-based radar analysis via PRCA extraction and context-augmented generation to reach 96.08% material identification accuracy on 41 everyday objects without task-specific training.
-
Egocentric Tactile and Proximity Sensors as Observation Priors for Humanoid Collision Avoidance
Raw proximity measurements can substitute for explicit object localization in humanoid collision avoidance if sensing range is sufficient, and sparse non-directional proximity signals train more efficiently than dense directional alternatives.