Unified Coarse-to-Fine Alignment for Video-Text Retrieval

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.

LoCoNet: Long-Short Context Network for Active Speaker Detection

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.

VindLU: A Recipe for Effective Video-and-Language Pretraining

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.

TALLFormer: Temporal Action Localization with Long-memory Transformer

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 very 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-based 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-art methods by a large margin, achieving an average mAP of 59.1% on THUMOS14 and 35.6% on ActivityNet-1.3. The code will be available in https://github.com/klauscc/TALLFormer.

Stochastic Backpropagation: A Memory Efficient Strategy for Training Video Models

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.

Using Single-Trial Representational Similarity Analysis with EEG to track semantic similarity in emotional word processing

Electroencephalography (EEG) is a powerful non-invasive brain imaging technique with a high temporal resolution that has seen extensive use across multiple areas of cognitive science research. This thesis adapts representational similarity analysis (RSA) to single-trial EEG datasets and introduces its principles to EEG researchers unfamiliar with multivariate analyses. We have two separate aims: 1. we want to explore the effectiveness of single-trial RSA on EEG datasets; 2. we want to utilize single-trial RSA and computational semantic models to investigate the role of semantic meaning in emotional word processing. We report two primary findings: 1. single-trial RSA on EEG datasets can produce meaningful and interpretable results given a high number of trials and subjects; 2. single-trial RSA reveals that emotional processing in the 500-800ms time window is associated with additional semantic analysis.

Efficient Deep Learning Pipelines for Accurate Cost Estimations Over Large Scale Query Workload

The use of deep learning models for forecasting the resource consumption patterns of SQL queries have recently been a popular area of study. With many companies using cloud platforms to power their data lakes for large scale analytic demands, these models form a critical part of the pipeline in managing cloud resource provisioning. While these models have demonstrated promising accuracy, training them over large scale industry workloads are expensive. Space inefficiencies of encoding techniques over large numbers of queries and excessive padding used to enforce shape consistency across diverse query plans implies 1) longer model training time and 2) the need for expensive, scaled up infrastructure to support batched training. In turn, we developed Prestroid, a tree convolution based data science pipeline that accurately predicts resource consumption patterns of query traces, but at a much lower cost. We evaluated our pipeline over 19K Presto OLAP queries from Grab, on a data lake of more than 20PB of data. Experimental results imply that our pipeline outperforms benchmarks on predictive accuracy, contributing to more precise resource prediction for large-scale workloads, yet also reduces per-batch memory footprint by 13.5x and per-epoch training time by 3.45x. We demonstrate direct cost savings of up to 13.2x for large batched model training over Microsoft Azure VMs.

Learning Directional Feature Maps for Cardiac MRI Segmentation

Cardiac MRI segmentation plays a crucial role in clinical diagnosis for evaluating personalized cardiac performance parameters. Due to the indistinct boundaries and heterogeneous intensity distributions in the cardiac MRI, most existing methods still suffer from two aspects of challenges: inter-class indistinction and intra-class inconsistency. To tackle these two problems, we propose a novel method to exploit the directional feature maps, which can simultaneously strengthen the differences between classes and the similarities within classes. Specifically, we perform cardiac segmentation and learn a direction field pointing away from the nearest cardiac tissue boundary to each pixel via a direction field (DF) module. Based on the learned direction field, we then propose a feature rectification and fusion (FRF) module to improve the original segmentation features, and obtain the final segmentation. The proposed modules are simple yet effective and can be flexibly added to any existing segmentation network without excessively increasing time and space complexity. We evaluate the proposed method on the 2017 MICCAI Automated Cardiac Diagnosis Challenge (ACDC) dataset and a large-scale self-collected dataset, showing good segmentation performance and robust generalization ability of the proposed method.