language: en
tags:
- tvp
- intel
- cvpr
- charades
license: other
datasets:
- charades
library_name: transformers
TVP base model
| Model Detail | Description |
|---|---|
| Model Authors | Yimeng Zhang, Xin Chen, Jinghan Jia, Sijia Liu, Ke Ding |
| Date | 2023 |
| Version | Base |
| Type | Text-Visual Prompting for Temporal Video Grounding |
| Paper or Other Resources | Base model: mosaicml/mpt-7b; Dataset: Charades |
| License | Other |
| Questions or Comments | Community Tab and Intel DevHub Discord |
| Intended Use | Description |
|---|---|
| Primary intended uses | The TVP model is designed for temporal video grounding (TVG), specifically to predict the start and end times of moments described by a text sentence within a long, untrimmed video. |
| Primary intended users | Researchers and developers working in the field of computer vision, particularly those focused on video understanding and cross-modal (text and video) tasks. |
| Out-of-scope uses | The model is not intended for real-time video processing or applications requiring 3D visual features extraction due to its design for efficiency with 2D features. |
Factors
Relevant factors: The model's performance may vary across different video content, such as variations in video quality, lighting conditions, or genres (e.g., action vs. dialogue-heavy scenes). Evaluation factors: Performance has been evaluated on benchmark datasets like Charades-STA and ActivityNet Captions, focusing on metrics relevant to temporal video grounding accuracy.
Metrics
Model performance measures: The model employs metrics such as the Temporal-Distance IoU (TDIoU) loss for efficient learning and performance evaluation in TVG tasks.
Experiments on two benchmark datasets, Charades-STA and ActivityNet Captions datasets, empirically show that the proposed TVP significantly boosts the performance of 2D TVG (e.g., 9.79% improvement on Charades-STA and 30.77% improvement on ActivityNet Captions) and achieves 5× inference acceleration over TVG using 3D visual features.
Training Data
The TVP model was pretrained on public datasets such as Charades.
Charades is dataset composed of 9848 videos of daily indoors activities collected through Amazon Mechanical Turk. 267 different users were presented with a sentence, that includes objects and actions from a fixed vocabulary, and they recorded a video acting out the sentence (like in a game of Charades). The dataset contains 66,500 temporal annotations for 157 action classes, 41,104 labels for 46 object classes, and 27,847 textual descriptions of the videos. This work was presented at ECCV2016.
Each video has been exhaustively annotated using consensus from 4 workers on the training set, and from 8 workers on the test set. Please refer to the updated accompanying publication for details. Please contact [email protected] for questions about the dataset.
Quantitative Analyses
Unitary results: Refer to Table 2 in the provided paper for TVP's performance on the Temporal Video Grounding task.
TVP base model
The TVP model was proposed in Text-Visual Prompting for Efficient 2D Temporal Video Grounding by Yimeng Zhang, Xin Chen, Jinghan Jia, Sijia Liu, Ke Ding. The goal of this model is to incorporate trainable prompts into both visual inputs and textual features to temporal video grounding(TVG) problems. It was introduced in this paper.
TVP got accepted to CVPR'23 conference.
Model description
The abstract from the paper is the following: In this paper, we study the problem of temporal video grounding (TVG), which aims to predict the starting/ending time points of moments described by a text sentence within a long untrimmed video. Benefiting from fine-grained 3D visual features, the TVG techniques have achieved remarkable progress in recent years. However, the high complexity of 3D convolutional neural networks (CNNs) makes extracting dense 3D visual features time-consuming, which calls for intensive memory and computing resources. Towards efficient TVG, we propose a novel text-visual prompting (TVP) framework, which incorporates optimized perturbation patterns (that we call ‘prompts’) into both visual inputs and textual features of a TVG model. In sharp contrast to 3D CNNs, we show that TVP allows us to effectively co-train vision encoder and language encoder in a 2D TVG model and improves the performance of cross-modal feature fusion using only low-complexity sparse 2D visual features. Further, we propose a Temporal-Distance IoU (TDIoU) loss for efficient learning of TVG. Experiments on two benchmark datasets, Charades-STA and ActivityNet Captions datasets, empirically show that the proposed TVP significantly boosts the performance of 2D TVG (e.g., 9.79% improvement on Charades-STA and 30.77% improvement on ActivityNet Captions) and achieves 5× inference acceleration over TVG using 3D visual features.
Intended uses & limitations(TODO)
You can use the raw model for temporal video grounding.
How to use
Here is how to use this model to get the logits of a given video and text in PyTorch:
import av
import cv2
import numpy as np
import torch
from huggingface_hub import hf_hub_download
from transformers import AutoProcessor, TvpForVideoGrounding
def pyav_decode(container, sampling_rate, num_frames, clip_idx, num_clips, target_fps):
'''
Convert the video from its original fps to the target_fps and decode the video with PyAV decoder.
Returns:
frames (tensor): decoded frames from the video. Return None if the no
video stream was found.
fps (float): the number of frames per second of the video.
'''
fps = float(container.streams.video[0].average_rate)
clip_size = sampling_rate * num_frames / target_fps * fps
delta = max(container.streams.video[0].frames - clip_size, 0)
start_idx = delta * clip_idx / num_clips
end_idx = start_idx + clip_size - 1
timebase = container.streams.video[0].duration / container.streams.video[0].frames
video_start_pts = int(start_idx * timebase)
video_end_pts = int(end_idx * timebase)
stream_name = {"video": 0}
seek_offset = max(video_start_pts - 1024, 0)
container.seek(seek_offset, any_frame=False, backward=True, stream=container.streams.video[0])
frames = {}
for frame in container.decode(**stream_name):
if frame.pts < video_start_pts:
continue
if frame.pts <= video_end_pts:
frames[frame.pts] = frame
else:
frames[frame.pts] = frame
break
frames = [frames[pts] for pts in sorted(frames)]
return frames, fps
def decode(container, sampling_rate, num_frames, clip_idx, num_clips, target_fps):
'''
Decode the video and perform temporal sampling.
Args:
container (container): pyav container.
sampling_rate (int): frame sampling rate (interval between two sampled frames).
num_frames (int): number of frames to sample.
clip_idx (int): if clip_idx is -1, perform random temporal sampling.
If clip_idx is larger than -1, uniformly split the video to num_clips
clips, and select the clip_idx-th video clip.
num_clips (int): overall number of clips to uniformly sample from the given video.
target_fps (int): the input video may have different fps, convert it to
the target video fps before frame sampling.
Returns:
frames (tensor): decoded frames from the video.
'''
assert clip_idx >= -2, "Not a valied clip_idx {}".format(clip_idx)
frames, fps = pyav_decode(container, sampling_rate, num_frames, clip_idx, num_clips, target_fps)
clip_size = sampling_rate * num_frames / target_fps * fps
index = torch.linspace(0, clip_size - 1, num_frames)
index = torch.clamp(index, 0, len(frames) - 1).long().tolist()
frames = [frames[idx] for idx in index]
frames = [frame.to_rgb().to_ndarray() for frame in frames]
frames = torch.from_numpy(np.stack(frames))
return frames
def get_resize_size(image, max_size):
'''
Args:
image: np.ndarray
max_size: The max size of height and width
Returns:
(height, width)
Note the height/width order difference >>> pil_img = Image.open("raw_img_tensor.jpg") >>> pil_img.size (640,
480) # (width, height) >>> np_img = np.array(pil_img) >>> np_img.shape (480, 640, 3) # (height, width, 3)
'''
height, width = image.shape[-2:]
if height >= width:
ratio = width * 1.0 / height
new_height = max_size
new_width = new_height * ratio
else:
ratio = height * 1.0 / width
new_width = max_size
new_height = new_width * ratio
size = {"height": int(new_height), "width": int(new_width)}
return size
file = hf_hub_download(repo_id="Intel/tvp_demo", filename="AK2KG.mp4", repo_type="dataset")
model = TvpForVideoGrounding.from_pretrained("Intel/tvp-base")
decoder_kwargs = dict(
container=av.open(file, metadata_errors="ignore"),
sampling_rate=1,
num_frames=model.config.num_frames,
clip_idx=0,
num_clips=1,
target_fps=3,
)
raw_sampled_frms = decode(**decoder_kwargs).permute(0, 3, 1, 2)
text = "a person is sitting on a bed."
processor = AutoProcessor.from_pretrained("Intel/tvp-base")
size = get_resize_size(raw_sampled_frms, model.config.max_img_size)
model_inputs = processor(
text=[text], videos=list(raw_sampled_frms.numpy()), return_tensors="pt", max_text_length=100, size=size
)
model_inputs["pixel_values"] = model_inputs["pixel_values"].to(model.dtype)
model_inputs["labels"] = torch.tensor([18.1, 0.0, 6.8])
output = model(**model_inputs)
print(f"The model's output is {output}")
def get_video_duration(filename):
cap = cv2.VideoCapture(filename)
if cap.isOpened():
rate = cap.get(5)
frame_num = cap.get(7)
duration = frame_num/rate
return duration
return -1
duration = get_video_duration(file)
timestamp = output['logits'].tolist()
start, end = round(timestamp[0][0]*duration, 1), round(timestamp[0][1]*duration, 1)
print(f"The time slot of the video corresponding to the text \"{text}\" is from {start}s to {end}s")
BibTeX entry and citation info
@inproceedings{zhang2023text,
title={Text-visual prompting for efficient 2d temporal video grounding},
author={Zhang, Yimeng and Chen, Xin and Jia, Jinghan and Liu, Sijia and Ding, Ke},
booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
pages={14794--14804},
year={2023}
}
Disclaimer The license on this model does not constitute legal advice. We are not responsible for the actions of third parties who use this model. Please cosult an attorney before using this model for commercial purposes.