Beyond Raw Videos: Understanding Edited Videos with Large Multimodal Model

The emerging video LMMs (Large Multimodal Models) have achieved significant improvements on generic video understanding in the form of VQA (Visual Question Answering), where the raw videos are captured by cameras. However, a large portion of videos in real-world applications are edited videos, \textit{e.g.}, users usually cut and add effects/modifications to the raw video before publishing it on social media platforms. The edited videos usually have high view counts but they are not covered in existing benchmarks of video LMMs, \textit{i.e.}, ActivityNet-QA, or VideoChatGPT benchmark. In this paper, we leverage the edited videos on a popular short video platform, \textit{i.e.}, TikTok, and build a video VQA benchmark (named EditVid-QA) covering four typical editing categories, i.e., effect, funny, meme, and game. Funny and meme videos benchmark nuanced understanding and high-level reasoning, while effect and game evaluate the understanding capability of artificial design. Most of the open-source video LMMs perform poorly on the EditVid-QA benchmark, indicating a huge domain gap between edited short videos on social media and regular raw videos. To improve the generalization ability of LMMs, we collect a training set for the proposed benchmark based on both Panda-70M/WebVid raw videos and small-scale TikTok/CapCut edited videos, which boosts the performance on the proposed EditVid-QA benchmark, indicating the effectiveness of high-quality training data. We also identified a serious issue in the existing evaluation protocol using the GPT-3.5 judge, namely a "sorry" attack, where a sorry-style naive answer can achieve an extremely high rating from the GPT judge, e.g., over 4.3 for correctness score on VideoChatGPT evaluation protocol. To avoid the "sorry" attacks, we evaluate results with GPT-4 judge and keyword filtering. The datasets will be released for academic purposes only.

CuMo: Scaling Multimodal LLM with Co-Upcycled Mixture-of-Experts

Recent advancements in Multimodal Large Language Models (LLMs) have focused primarily on scaling by increasing text-image pair data and enhancing LLMs to improve performance on multimodal tasks. However, these scaling approaches are computationally expensive and overlook the significance of improving model capabilities from the vision side. Inspired by the successful applications of Mixture-of-Experts (MoE) in LLMs, which improves model scalability during training while keeping inference costs similar to those of smaller models, we propose CuMo. CuMo incorporates Co-upcycled Top-K sparsely-gated Mixture-of-experts blocks into both the vision encoder and the MLP connector, thereby enhancing the multimodal LLMs with minimal additional activated parameters during inference. CuMo first pre-trains the MLP blocks and then initializes each expert in the MoE block from the pre-trained MLP block during the visual instruction tuning stage. Auxiliary losses are used to ensure a balanced loading of experts. CuMo outperforms state-of-the-art multimodal LLMs across various VQA and visual-instruction-following benchmarks using models within each model size group, all while training exclusively on open-sourced datasets. The code and model weights for CuMo are open-sourced at https://github.com/SHI-Labs/CuMo.

QuadraNet V2: Efficient and Sustainable Training of High-Order Neural Networks with Quadratic Adaptation

Machine learning is evolving towards high-order models that necessitate pre-training on extensive datasets, a process associated with significant overheads. Traditional models, despite having pre-trained weights, are becoming obsolete due to architectural differences that obstruct the effective transfer and initialization of these weights. To address these challenges, we introduce a novel framework, QuadraNet V2, which leverages quadratic neural networks to create efficient and sustainable high-order learning models. Our method initializes the primary term of the quadratic neuron using a standard neural network, while the quadratic term is employed to adaptively enhance the learning of data non-linearity or shifts. This integration of pre-trained primary terms with quadratic terms, which possess advanced modeling capabilities, significantly augments the information characterization capacity of the high-order network. By utilizing existing pre-trained weights, QuadraNet V2 reduces the required GPU hours for training by 90\% to 98.4\% compared to training from scratch, demonstrating both efficiency and effectiveness.

Steam Recommendation System

We aim to leverage the interactions between users and items in the Steam community to build a game recommendation system that makes personalized suggestions to players in order to boost Steam's revenue as well as improve the users' gaming experience. The whole project is built on Apache Spark and deals with Big Data. The final output of the project is a recommendation system that gives a list of the top 5 items that the users will possibly like.6

Secure UAV-to-Ground MIMO Communications: Joint Transceiver and Location Optimization

Unmanned aerial vehicles (UAVs) are foreseen to constitute promising airborne communication devices as a benefit of their superior channel quality. But UAV-to-ground (U2G) communications are vulnerable to eavesdropping. Hence, we conceive a sophisticated physical layer security solution for improving the secrecy rate of multi-antenna aided U2G systems. Explicitly, the secrecy rate of the U2G MIMO wiretap channels is derived by using random matrix theory. The resultant explicit expression is then applied in the joint optimization of the MIMO transceiver and the UAV location relying on an alternating optimization technique. Our numerical results show that the joint transceiver and location optimization conceived facilitates secure communications even in the challenging scenario, where the legitimate channel of confidential information is inferior to the eavesdropping channel.

SC-Transformer++: Structured Context Transformer for Generic Event Boundary Detection

This report presents the algorithm used in the submission of Generic Event Boundary Detection (GEBD) Challenge at CVPR 2022. In this work, we improve the existing Structured Context Transformer (SC-Transformer) method for GEBD. Specifically, a transformer decoder module is added after transformer encoders to extract high quality frame features. The final classification is performed jointly on the results of the original binary classifier and a newly introduced multi-class classifier branch. To enrich motion information, optical flow is introduced as a new modality. Finally, model ensemble is used to further boost performance. The proposed method achieves 86.49% F1 score on Kinetics-GEBD test set. which improves 2.86% F1 score compared to the previous SOTA method.

Structured Context Transformer for Generic Event Boundary Detection

Generic Event Boundary Detection (GEBD) aims to detect moments where humans naturally perceive as event boundaries. In this paper, we present Structured Context Transformer (or SC-Transformer) to solve the GEBD task, which can be trained in an end-to-end fashion. Specifically, we use the backbone convolutional neural network (CNN) to extract the features of each video frame. To capture temporal context information of each frame, we design the structure context transformer (SC-Transformer) by re-partitioning input frame sequence. Note that, the overall computation complexity of SC-Transformer is linear to the video length. After that, the group similarities are computed to capture the differences between frames. Then, a lightweight fully convolutional network is used to determine the event boundaries based on the grouped similarity maps. To remedy the ambiguities of boundary annotations, the Gaussian kernel is adopted to preprocess the ground-truth event boundaries to further boost the accuracy. Extensive experiments conducted on the challenging Kinetics-GEBD and TAPOS datasets demonstrate the effectiveness of the proposed method compared to the state-of-the-art methods.

End-to-End Compressed Video Representation Learning for Generic Event Boundary Detection

Generic event boundary detection aims to localize the generic, taxonomy-free event boundaries that segment videos into chunks. Existing methods typically require video frames to be decoded before feeding into the network, which demands considerable computational power and storage space. To that end, we propose a new end-to-end compressed video representation learning for event boundary detection that leverages the rich information in the compressed domain, i.e., RGB, motion vectors, residuals, and the internal group of pictures (GOP) structure, without fully decoding the video. Specifically, we first use the ConvNets to extract features of the I-frames in the GOPs. After that, a light-weight spatial-channel compressed encoder is designed to compute the feature representations of the P-frames based on the motion vectors, residuals and representations of their dependent I-frames. A temporal contrastive module is proposed to determine the event boundaries of video sequences. To remedy the ambiguities of annotations and speed up the training process, we use the Gaussian kernel to preprocess the ground-truth event boundaries. Extensive experiments conducted on the Kinetics-GEBD dataset demonstrate that the proposed method achieves comparable results to the state-of-the-art methods with $4.5\times$ faster running speed.

Generic Event Boundary Detection Challenge at CVPR 2021 Technical Report: Cascaded Temporal Attention Network (CASTANET)

This report presents the approach used in the submission of Generic Event Boundary Detection (GEBD) Challenge at CVPR21. In this work, we design a Cascaded Temporal Attention Network (CASTANET) for GEBD, which is formed by three parts, the backbone network, the temporal attention module, and the classification module. Specifically, the Channel-Separated Convolutional Network (CSN) is used as the backbone network to extract features, and the temporal attention module is designed to enforce the network to focus on the discriminative features. After that, the cascaded architecture is used in the classification module to generate more accurate boundaries. In addition, the ensemble strategy is used to further improve the performance of the proposed method. The proposed method achieves 83.30% F1 score on Kinetics-GEBD test set, which improves 20.5% F1 score compared to the baseline method. Code is available at https://github.com/DexiangHong/Cascade-PC.

Adaptive Wing Loss for Robust Face Alignment via Heatmap Regression

Heatmap regression has became one of the mainstream approaches to localize facial landmarks. As Convolutional Neural Network (CNN) and Recurrent Neural Network (RNN) are becoming popular in solving computer vision tasks, extensive research has been done on these architectures. However, the loss function for heatmap regression is rarely studied. In this paper, we analyze the ideal loss function properties for heatmap regression in face alignment problems. Then we propose a novel loss function, named Adaptive Wing loss, that is able to adapt its shape to different types of ground truth heatmap pixels. This adaptability decreases the loss to zero on foreground pixels while leaving some loss on background pixels. To address the imbalance between foreground and background pixels, we also propose Weighted Loss Map, which assigns high weights on foreground and difficult background pixels to help training process focus more on pixels that are crucial to landmark localization. To further improve face alignment accuracy, we introduce boundary prediction and CoordConv with boundary coordinates. Extensive experiments on different benchmarks, including COFW, 300W and WFLW, show our approach outperforms the state-of-the-art by a significant margin on various evaluation metrics. Besides, the Adaptive Wing loss also helps other heatmap regression tasks. Code will be made publicly available.