Search Results for author:
Found 8 papers, 5 papers with code
LIP: Local Importance-based Pooling
Spatial downsampling layers are favored in convolutional neural networks (CNNs) to downscale feature maps for larger receptive fields and less memory consumption.
Ranked #147 on
Object Detection
on COCO test-dev
(using extra training data)
Mutual Supervision for Dense Object Detection
In this paper, we break the convention of the same training samples for these two heads in dense detectors and explore a novel supervisory paradigm, termed as Mutual Supervision (MuSu), to respectively and mutually assign training samples for the classification and regression head to ensure this consistency.
AdaMixer: A Fast-Converging Query-Based Object Detector
The recent query-based object detectors break this convention by decoding image features with a set of learnable queries.
SparseFormer: Sparse Visual Recognition via Limited Latent Tokens
In this paper, we challenge this dense paradigm and present a new method, coined SparseFormer, to imitate human's sparse visual recognition in an end-to-end manner.
Sparse Representation-based Classification
Video Classification
Bootstrapping SparseFormers from Vision Foundation Models
In this paper, we propose to bootstrap SparseFormers from ViT-based vision foundation models in a simple and efficient way.
STMixer: A One-Stage Sparse Action Detector
First, we present a query-based adaptive feature sampling module, which endows the detector with the flexibility of mining a group of discriminative features from the entire spatio-temporal domain.
Boundary-Aware Cascade Networks for Temporal Action Segmentation
To address these problems, we present a new boundary-aware cascade network by introducing two novel components.
Ranked #14 on
Action Segmentation
on GTEA
