Feng Cheng

Feng Cheng, Xizi Wang, Jie Lei et al.

The last several years have witnessed remarkable progress in video-and-language (VidL) understanding. However, most modern VidL approaches use complex and specialized model architectures and sophisticated pretraining protocols, making the reproducibility, analysis and comparisons of these frameworks difficult. Hence, instead of proposing yet another new VidL model, this paper conducts a thorough empirical study demystifying the most important factors in the VidL model design. Among the factors that we investigate are (i) the spatiotemporal architecture design, (ii) the multimodal fusion schemes, (iii) the pretraining objectives, (iv) the choice of pretraining data, (v) pretraining and finetuning protocols, and (vi) dataset and model scaling. Our empirical study reveals that the most important design factors include: temporal modeling, video-to-text multimodal fusion, masked modeling objectives, and joint training on images and videos. Using these empirical insights, we then develop a step-by-step recipe, dubbed VindLU, for effective VidL pretraining. Our final model trained using our recipe achieves comparable or better than state-of-the-art results on several VidL tasks without relying on external CLIP pretraining. In particular, on the text-to-video retrieval task, our approach obtains 61.2% on DiDeMo, and 55.0% on ActivityNet, outperforming current SOTA by 7.8% and 6.1% respectively. Furthermore, our model also obtains state-of-the-art video question-answering results on ActivityNet-QA, MSRVTT-QA, MSRVTT-MC and TVQA. Our code and pretrained models are publicly available at: https://github.com/klauscc/VindLU.

Ziyang Wang, Yi-Lin Sung, Feng Cheng et al.

The canonical approach to video-text retrieval leverages a coarse-grained or fine-grained alignment between visual and textual information. However, retrieving the correct video according to the text query is often challenging as it requires the ability to reason about both high-level (scene) and low-level (object) visual clues and how they relate to the text query. To this end, we propose a Unified Coarse-to-fine Alignment model, dubbed UCoFiA. Specifically, our model captures the cross-modal similarity information at different granularity levels. To alleviate the effect of irrelevant visual clues, we also apply an Interactive Similarity Aggregation module (ISA) to consider the importance of different visual features while aggregating the cross-modal similarity to obtain a similarity score for each granularity. Finally, we apply the Sinkhorn-Knopp algorithm to normalize the similarities of each level before summing them, alleviating over- and under-representation issues at different levels. By jointly considering the crossmodal similarity of different granularity, UCoFiA allows the effective unification of multi-grained alignments. Empirically, UCoFiA outperforms previous state-of-the-art CLIP-based methods on multiple video-text retrieval benchmarks, achieving 2.4%, 1.4% and 1.3% improvements in text-to-video retrieval R@1 on MSR-VTT, Activity-Net, and DiDeMo, respectively. Our code is publicly available at https://github.com/Ziyang412/UCoFiA.

Feng Cheng, Gedas Bertasius

Most modern approaches in temporal action localization divide this problem into two parts: (i) short-term feature extraction and (ii) long-range temporal boundary localization. Due to the high GPU memory cost caused by processing long untrimmed videos, many methods sacrifice the representational power of the short-term feature extractor by either freezing the backbone or using a small spatial video resolution. This issue becomes even worse with the recent video transformer models, many of which have quadratic memory complexity. To address these issues, we propose TALLFormer, a memory-efficient and end-to-end trainable Temporal Action Localization Transformer with Long-term memory. Our long-term memory mechanism eliminates the need for processing hundreds of redundant video frames during each training iteration, thus, significantly reducing the GPU memory consumption and training time. These efficiency savings allow us (i) to use a powerful video transformer feature extractor without freezing the backbone or reducing the spatial video resolution, while (ii) also maintaining long-range temporal boundary localization capability. With only RGB frames as input and no external action recognition classifier, TALLFormer outperforms previous state-of-the-arts by a large margin, achieving an average mAP of 59.1% on THUMOS14 and 35.6% on ActivityNet-1.3. The code is public available: https://github.com/klauscc/TALLFormer.

Xizi Wang, Feng Cheng, Gedas Bertasius et al.

Active Speaker Detection (ASD) aims to identify who is speaking in each frame of a video. ASD reasons from audio and visual information from two contexts: long-term intra-speaker context and short-term inter-speaker context. Long-term intra-speaker context models the temporal dependencies of the same speaker, while short-term inter-speaker context models the interactions of speakers in the same scene. These two contexts are complementary to each other and can help infer the active speaker. Motivated by these observations, we propose LoCoNet, a simple yet effective Long-Short Context Network that models the long-term intra-speaker context and short-term inter-speaker context. We use self-attention to model long-term intra-speaker context due to its effectiveness in modeling long-range dependencies, and convolutional blocks that capture local patterns to model short-term inter-speaker context. Extensive experiments show that LoCoNet achieves state-of-the-art performance on multiple datasets, achieving an mAP of 95.2%(+1.1%) on AVA-ActiveSpeaker, 68.1%(+22%) on Columbia dataset, 97.2%(+2.8%) on Talkies dataset and 59.7%(+8.0%) on Ego4D dataset. Moreover, in challenging cases where multiple speakers are present, or face of active speaker is much smaller than other faces in the same scene, LoCoNet outperforms previous state-of-the-art methods by 3.4% on the AVA-ActiveSpeaker dataset. The code will be released at https://github.com/SJTUwxz/LoCoNet_ASD.

Feng Cheng, Ziyang Wang, Yi-Lin Sung et al.

We present a parameter-efficient method for continual video question-answering (VidQA) learning. Our method, named DAM, uses the proposed Dynamic Adapter Merging to (i) mitigate catastrophic forgetting, (ii) enable efficient adaptation to continually arriving datasets, (iii) handle inputs from unknown datasets during inference, and (iv) enable knowledge sharing across similar dataset domains. Given a set of continually streaming VidQA datasets, we sequentially train dataset-specific adapters for each dataset while freezing the parameters of a large pretrained video-language backbone. During inference, given a video-question sample from an unknown domain, our method first uses the proposed non-parametric router function to compute a probability for each adapter, reflecting how relevant that adapter is to the current video-question input instance. Subsequently, the proposed dynamic adapter merging scheme aggregates all the adapter weights into a new adapter instance tailored for that particular test sample to compute the final VidQA prediction, mitigating the impact of inaccurate router predictions and facilitating knowledge sharing across domains. Our DAM model outperforms prior state-of-the-art continual learning approaches by 9.1% while exhibiting 1.9% less forgetting on 6 VidQA datasets spanning various domains. We further extend DAM to continual image classification and image QA and outperform prior methods by a large margin. The code is publicly available at: https://github.com/klauscc/DAM

Shihan Dou, Yueming Wu, Wenxuan Li et al.

Due to its powerful automatic feature extraction, deep learning (DL) has been widely used in source code vulnerability detection. However, although it performs well on artificial datasets, its performance is not satisfactory when detecting real-world vulnerabilities due to the high complexity of real-world samples. In this paper, we propose to train DL-based vulnerability detection models in a human-learning manner, that is, start with the simplest samples and then gradually transition to difficult knowledge. Specifically, we design a novel framework (Humer) that can enhance the detection ability of DL-based vulnerability detectors. To validate the effectiveness of Humer, we select five state-of-the-art DL-based vulnerability detection models (TokenCNN, VulDeePecker, StatementGRU, ASTGRU, and Devign) to complete our evaluations. Through the results, we find that the use of Humer can increase the F1 of these models by an average of 10.5%. Moreover, Humer can make the model detect up to 16.7% more real-world vulnerabilities. Meanwhile, we also conduct a case study to uncover vulnerabilities from real-world open source products by using these enhanced DL-based vulnerability detectors. Through the results, we finally discover 281 unreported vulnerabilities in NVD, of which 98 have been silently patched by vendors in the latest version of corresponding products, but 159 still exist in the products.

Feng Cheng, Mingze Xu, Yuanjun Xiong et al.

We propose a memory efficient method, named Stochastic Backpropagation (SBP), for training deep neural networks on videos. It is based on the finding that gradients from incomplete execution for backpropagation can still effectively train the models with minimal accuracy loss, which attributes to the high redundancy of video. SBP keeps all forward paths but randomly and independently removes the backward paths for each network layer in each training step. It reduces the GPU memory cost by eliminating the need to cache activation values corresponding to the dropped backward paths, whose amount can be controlled by an adjustable keep-ratio. Experiments show that SBP can be applied to a wide range of models for video tasks, leading to up to 80.0% GPU memory saving and 10% training speedup with less than 1% accuracy drop on action recognition and temporal action detection.