Search Results for author:
Found 17 papers, 10 papers with code
Local Correlation Consistency for Knowledge Distillation
Sufficient knowledge extraction from the teacher network plays a critical role in the knowledge distillation task to improve the performance of the student network.
Mask-Enhanced Segment Anything Model for Tumor Lesion Semantic Segmentation
Tumor lesion segmentation on CT or MRI images plays a critical role in cancer diagnosis and treatment planning.
LLMs as Visual Explainers: Advancing Image Classification with Evolving Visual Descriptions
We attribute this to two primary factors: 1) the reliance on single-turn textual interactions with LLMs, leading to a mismatch between generated text and visual concepts for VLMs; 2) the oversight of the inter-class relationships, resulting in descriptors that fail to differentiate similar classes effectively.
DiffDance: Cascaded Human Motion Diffusion Model for Dance Generation
To address these limitations, we present a novel cascaded motion diffusion model, DiffDance, designed for high-resolution, long-form dance generation.
Object-Aware Distillation Pyramid for Open-Vocabulary Object Detection
When extracting object knowledge from PVLMs, the former adaptively transforms object proposals and adopts object-aware mask attention to obtain precise and complete knowledge of objects.
Ranked #14 on
Open Vocabulary Object Detection
on MSCOCO
Masked Contrastive Pre-Training for Efficient Video-Text Retrieval
Our MAC aims to reduce video representation's spatial and temporal redundancy in the VidLP model by a mask sampling mechanism to improve pre-training efficiency.
Ranked #37 on
Video Retrieval
on MSR-VTT-1kA
(using extra training data)
Video Background Music Generation: Dataset, Method and Evaluation
We believe our dataset, benchmark model, and evaluation metric will boost the development of video background music generation.
HEAD: HEtero-Assists Distillation for Heterogeneous Object Detectors
We observe that the core difficulty for heterogeneous KD (hetero-KD) is the significant semantic gap between the backbone features of heterogeneous detectors due to the different optimization manners.
TR-MOT: Multi-Object Tracking by Reference
RS takes previous detected results as references to aggregate the corresponding features from the combined features of the adjacent frames and makes a one-to-one track state prediction for each reference in parallel.
GEN-VLKT: Simplify Association and Enhance Interaction Understanding for HOI Detection
In this paper, we reveal and address the disadvantages of the conventional query-driven HOI detectors from the two aspects.
Ranked #12 on
Human-Object Interaction Detection
on HICO-DET
Mining the Benefits of Two-stage and One-stage HOI Detection
To this end, we propose a novel one-stage framework with disentangling human-object detection and interaction classification in a cascade manner.
Ranked #7 on
Human-Object Interaction Detection
on V-COCO
Human-centric Relation Segmentation: Dataset and Solution
For the above exemplar case, our HRS task produces results in the form of relation triplets <girl [left hand], hold, book> and exacts segmentation masks of the book, with which the robot can easily accomplish the grabbing task.
Reformulating HOI Detection as Adaptive Set Prediction
To attain this, we map a trainable interaction query set to an interaction prediction set with a transformer.
Ranked #29 on
Human-Object Interaction Detection
on HICO-DET
(using extra training data)
Human-centric Spatio-Temporal Video Grounding With Visual Transformers
HC-STVG is a video grounding task that requires both spatial (where) and temporal (when) localization.
CentripetalNet: Pursuing High-quality Keypoint Pairs for Object Detection
CentripetalNet predicts the position and the centripetal shift of the corner points and matches corners whose shifted results are aligned.
PPDM: Parallel Point Detection and Matching for Real-time Human-Object Interaction Detection
Human and object points are the center of the detection boxes, and the interaction point is the midpoint of the human and object points.
Ranked #25 on
Human-Object Interaction Detection
on V-COCO
A Real-Time Cross-modality Correlation Filtering Method for Referring Expression Comprehension
RCCF reformulates the referring expression comprehension as a correlation filtering process.
