HyperAIHyperAI
HomeConsoleDocsNewsPapersTutorialsDatasetsWikiSOTALLM ModelsGPU LeaderboardEvents
Search
About
HyperAIHyperAI

Command Palette

Search for a command to run...

Human Object Interaction Detection On Hico

Metrics

mAP

Results

Performance results of various models on this benchmark

Paper TitleRepository
Ours (PViC+)46.49Dynamic Scene Understanding from Vision-Language Representations-
RLIPv2 (Swin-L)45.09RLIPv2: Fast Scaling of Relational Language-Image Pre-training
PViC-SwinL44.32Exploring Predicate Visual Context in Detecting Human-Object Interactions
SOV-STG (Swin-L)43.35Focusing on what to decode and what to train: SOV Decoding with Specific Target Guided DeNoising and Vision Language Advisor
DiffHOI41.50Boosting Human-Object Interaction Detection with Text-to-Image Diffusion Model
ViPLO37.22ViPLO: Vision Transformer based Pose-Conditioned Self-Loop Graph for Human-Object Interaction Detection
FGAHOI37.18FGAHOI: Fine-Grained Anchors for Human-Object Interaction Detection
ERNet36.89ERNet: Efficient and Reliable Human-Object Interaction Detection-
CQL+GEN-VLKT-L36.03Category Query Learning for Human-Object Interaction Classification
QAHOI (Swin-L)35.78QAHOI: Query-Based Anchors for Human-Object Interaction Detection
CQL+GEN-VLKT-B35.36Category Query Learning for Human-Object Interaction Classification
Body Part Interactiveness35.15Mining Cross-Person Cues for Body-Part Interactiveness Learning in HOI Detection
GEN-VLKT-R10134.95GEN-VLKT: Simplify Association and Enhance Interaction Understanding for HOI Detection
HOIGen34.84Unseen No More: Unlocking the Potential of CLIP for Generative Zero-shot HOI Detection
PViC-R5034.69Exploring Predicate Visual Context in Detecting Human-Object Interactions
HOICLIP34.69HOICLIP: Efficient Knowledge Transfer for HOI Detection with Vision-Language Models
MUREN32.87Relational Context Learning for Human-Object Interaction Detection
RLIP-ParSe (ResNet-50)32.84RLIP: Relational Language-Image Pre-training for Human-Object Interaction Detection
ParSe (ResNet-101)32.76RLIP: Relational Language-Image Pre-training for Human-Object Interaction Detection
UPT-R101-DC532.62Efficient Two-Stage Detection of Human-Object Interactions with a Novel Unary-Pairwise Transformer
0 of 55 row(s) selected.
Human Object Interaction Detection On Hico | SOTA | HyperAI