issues
search
fredzzhang
/
pvic
[ICCV'23] Official PyTorch implementation for paper "Exploring Predicate Visual Context in Detecting Human-Object Interactions"
BSD 3-Clause "New" or "Revised" License
67
stars
8
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
data set
#61
LUYUuuum
opened
1 day ago
3
Training error
#60
YangJae96
opened
1 week ago
5
training error for hicodet
#59
hurrrrrrtui
closed
3 weeks ago
2
video data
#58
LHYUNMIN
closed
3 weeks ago
1
Problem about detector performance against hoi performance
#57
shan-jianqing
closed
1 month ago
1
Swin backbone trained weights
#56
YangJae96
closed
1 month ago
3
Get grad of inputs
#55
xiezouqu
closed
4 months ago
2
How to obtain the metrics of Default (DT) mode and Known-Object (KO) mode on the hico-det dataset?
#54
AngleBeats147753
closed
4 months ago
1
Training ERROR
#53
xiezouqu
closed
4 months ago
10
fix typo in paths
#52
fredzzhang
closed
5 months ago
0
Minor typo in readme setup instructions
#51
morrisalp
closed
5 months ago
1
PViC Fine-tune
#50
AlineAssakaTani
closed
5 months ago
1
Could you please provide the code for QPIC's heatmap visualization？
#49
thunderbolt-fire
closed
5 months ago
6
NaN when I use a DETR that I fine tuned
#48
JonasFerreiraSilva
closed
6 months ago
6
RuntimeError: CUDA error: invalid device ordinal
#47
mansooreh1
closed
6 months ago
4
A problem regarding inference and visulization
#46
kagawa588
closed
7 months ago
1
some question about hyperparameters of PViC with resnet50
#45
jasminethurder
closed
7 months ago
2
HICO-DET link and download script seems down
#44
RenatoNogFer
closed
9 months ago
2
Zero-shot inference for unseen verbs
#43
hutuo1213
closed
10 months ago
2
add `--use-checkpoint` command for `SwinL` backbone
#42
fredzzhang
closed
11 months ago
0
[Bug] Cannot load the parameters of the advanced model (SwinL-based) on HICO-DET
#41
QihanZhao
closed
9 months ago
6
Random seeds in training
#40
hutuo1213
closed
11 months ago
4
Mistake when skipping images.
#39
hutuo1213
closed
1 year ago
2
add license
#38
fredzzhang
closed
1 year ago
0
update the documentation & fix inference code
#37
fredzzhang
closed
1 year ago
0
hyperparameters
#36
131413ljk
closed
1 year ago
4
Experimental results on V-COCO
#35
winnerwu6
closed
9 months ago
7
Timeline for upadating Readme.md
#34
ZhouGuangP
closed
1 year ago
4
About pre-trained weight of object detector
#33
xz-123-new
closed
1 year ago
5
What's the module "upt" in inference.py?
#32
musicBoxes
closed
1 year ago
2
The problem in your code???
#31
ZhouGuangP
closed
1 year ago
2
How to inference on single image and draw the bbox on the image?
#30
aixiaodewugege
closed
1 year ago
2
The loss is NaN during training
#29
hutuo1213
closed
1 year ago
5
update `pocket` to include the `advis` package
#28
fredzzhang
closed
1 year ago
0
update evaluation utilities for V-COCO
#27
fredzzhang
closed
1 year ago
0
update the evaluation utilities for v-coco
#26
fredzzhang
closed
1 year ago
0
add options to obtain object features via `RoIAlign`
#25
fredzzhang
closed
1 year ago
0
add advanced variants of `detr` for object detection
#24
fredzzhang
closed
1 year ago
0
restructure the codebase
#23
fredzzhang
closed
1 year ago
0
multiple minor changes
#22
fredzzhang
closed
1 year ago
0
coordinate all dropout parameters
#21
fredzzhang
closed
1 year ago
0
add `PositionalEmbedding` to human-object queries in decoder `SelfAttention`
#20
fredzzhang
closed
1 year ago
0
replace `ModifiedEncoder` with standard `TransformerEncoder`
#19
fredzzhang
closed
1 year ago
0
apply modulated `PositionalEmbedding` via concatenation
#18
fredzzhang
closed
1 year ago
0
change the temperature in `PositionalEmbeddingSine` to `20`
#17
fredzzhang
closed
1 year ago
0
convert `detr` into an importable package
#16
fredzzhang
closed
1 year ago
0
move `drop_last` argument to `DistributedSampler`
#15
fredzzhang
closed
1 year ago
0
add argument for the number of encoder layers
#14
fredzzhang
closed
1 year ago
0
add `SelfAttention` between object instances
#13
fredzzhang
closed
1 year ago
0
have separate reference points for humans and objects
#12
fredzzhang
closed
1 year ago
0
Next