<?xml version="1.0" encoding="UTF-8"?><rss xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:content="http://purl.org/rss/1.0/modules/content/" xmlns:atom="http://www.w3.org/2005/Atom" version="2.0" xmlns:cc="http://cyber.law.harvard.edu/rss/creativeCommonsRssModule.html">
    <channel>
        <title><![CDATA[Multi-Modal Understanding - Medium]]></title>
        <description><![CDATA[Papers which proposes deep learning models for video-text or image-text understanding are reviewed in detail. - Medium]]></description>
        <link>https://medium.com/video-text-understanding?source=rss----e5314efe8d52---4</link>
        <image>
            <url>https://cdn-images-1.medium.com/proxy/1*TGH72Nnw24QL3iV9IOm4VA.png</url>
            <title>Multi-Modal Understanding - Medium</title>
            <link>https://medium.com/video-text-understanding?source=rss----e5314efe8d52---4</link>
        </image>
        <generator>Medium</generator>
        <lastBuildDate>Mon, 16 Nov 2026 03:16:44 GMT</lastBuildDate>
        <atom:link href="https://medium.com/feed/video-text-understanding" rel="self" type="application/rss+xml"/>
        <webMaster><![CDATA[yourfriends@medium.com]]></webMaster>
        <atom:link href="http://medium.superfeedr.com/" rel="hub"/>
        <item>
            <title><![CDATA[Paper Review: Learning Temporal Video Procedure Segmentation from an Automatically Collected Large…]]></title>
            <link>https://medium.com/video-text-understanding/paper-review-learning-temporal-video-procedure-segmentation-from-an-automatically-collected-large-1cfb618b9339?source=rss----e5314efe8d52---4</link>
            <guid isPermaLink="false">https://medium.com/p/1cfb618b9339</guid>
            <category><![CDATA[deep-learning]]></category>
            <category><![CDATA[recipe]]></category>
            <category><![CDATA[video-text-understanding]]></category>
            <dc:creator><![CDATA[Yunusemre Özköse]]></dc:creator>
            <pubDate>Mon, 04 Jul 2022 21:48:16 GMT</pubDate>
            <atom:updated>2022-07-05T07:12:23.683Z</atom:updated>
            <content:encoded><![CDATA[<h3>Paper Review: Learning Temporal Video Procedure Segmentation from an Automatically Collected Large Dataset</h3><h3>Introduction</h3><p>In a video, there might be several actions like cooking, walking, swimming, eating, etc... These actions might naturally be following to another one like eating after cooking. At this point, the video contains several segments, ex.: 1)preparing tomatoes 2)cutting potatoes 3)mixing them 4)cooking 5)eating. The video segmentation task is defined as segmenting these actions in the given video. Authors define 2 sub-task of video segmentation: Video Action Segmentation (VAS) and Video Procedure Segmentation (VPS).</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*tCOc9_gd4XkRm1V4LnWbWg.png" /></figure><p>The action segmentation task requires a set of action names and separates a video into segments with predicted action labels. However, procedure segmentation doesn’t need labels and is in charge of predicting only action boundaries. In this paper, the authors introduce a procedural video dataset and propose a procedure segmentation method.</p><h3>TIPS Dataset</h3><p>There are 4 key points of the proposed dataset:</p><ul><li>Scale: It is the largest procedural dataset up to now.</li><li>Diversity: There are multiple domains like cooking, gardening, etc…</li><li>Contiguity: YouCook2 segments might be different parts of the video, and there might be gaps between each segment in the video. However, the proposed dataset guarantees that segments are following the other one.</li><li>Auto-generated: Dataset is automatically collected via a pipeline.</li></ul><p>It is so fancy that the dataset is automatically generated with a pipeline, we can extend the dataset for a specific domain such as cooking. I know this example is contrary to the second point, but if a researcher focuses on a domain, it is very useful to extend this dataset in an automatic manner.</p><p>Workflow of collecting data automatically:</p><ol><li>Collecting instructional videos: search the video title with keywords like ”How to” or ”ways to” etc. as instructional videos.</li><li>Select well-organized videos: match the speech text that explicitly mention the keywords like “step 1”, “step two”, and so on.</li><li>Construct segment labels: After selecting videos with the first 2 steps, extract annotations from metadata. Youtube videos already have timestamps of segments. Authors map steps to these segments. Hence labels are automatically extracted.</li></ol><p>The number of samples for the top 20 categories is shown below.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*a0vNYk24mj41S6lElots_A.png" /></figure><h3>Multi-modal Transformer with Gaussian Boundary Detection (MT-GBD)</h3><p>The proposed model MT-GBD aims to separate each procedural step in the given video. Pre-trained SlowFast ResNeXt-101 is used to extract features from the given video where video ∈ R(Mxwxhxc) and V(f) = feature ∈ R(Mxd’). Then semantic feature is extracted with</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*aGXMnj3q5cDe07-r-vQmdQ.png" /></figure><p>E(p) is positional embedding and added to visual feature for encoding position information. Then text/transcription features are extracted with BERT model:</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*uqF6koGmWX0EljWKMDSILQ.png" /></figure><figure><img alt="" src="https://cdn-images-1.medium.com/max/746/1*2pkcvZ_PsWwFD4fNddgV4g.png" /></figure><p>In the end, V ∈ R(Mxd) and L ∈ R(Nxd) where M is maximum video length, N is maximum transcription length, and d is feature dimension. After that, both visual and textual features are given to self-attention layers. Then multi-had attention module is used to fuse visual and textual parts. Then convolution layers are applied to video masks of self-attention. Finally, these outputs are mapped to a final layer R(Mx2) where there are 2 different output types: boundary/non-boundary. They use gaussian boundry detection during training and non-maximum suppression during test time. The overall architecture is shown below.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*KAMQ3zv3lwf3Pq2bsKNTlw.png" /></figure><h3>Note</h3><p>I couldn’t find the website of the dataset, the paper is published recently and I think the authors will make it publically available soon.</p><p>[1] Ji, Lei, et al. “Learning Temporal Video Procedure Segmentation from an Automatically Collected Large Dataset.” <em>Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision</em>. 2022.</p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=1cfb618b9339" width="1" height="1" alt=""><hr><p><a href="https://medium.com/video-text-understanding/paper-review-learning-temporal-video-procedure-segmentation-from-an-automatically-collected-large-1cfb618b9339">Paper Review: Learning Temporal Video Procedure Segmentation from an Automatically Collected Large…</a> was originally published in <a href="https://medium.com/video-text-understanding">Multi-Modal Understanding</a> on Medium, where people are continuing the conversation by highlighting and responding to this story.</p>]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[Paper Review: Scaling Egocentric Vision: The EPIC-KITCHENS Dataset]]></title>
            <link>https://medium.com/video-text-understanding/paper-review-scaling-egocentric-vision-the-epic-kitchens-dataset-5e71ed117413?source=rss----e5314efe8d52---4</link>
            <guid isPermaLink="false">https://medium.com/p/5e71ed117413</guid>
            <category><![CDATA[video-text-understanding]]></category>
            <category><![CDATA[recipe]]></category>
            <category><![CDATA[deep-learning]]></category>
            <category><![CDATA[cooking]]></category>
            <dc:creator><![CDATA[Yunusemre Özköse]]></dc:creator>
            <pubDate>Sat, 02 Jul 2022 22:37:23 GMT</pubDate>
            <atom:updated>2022-07-02T22:37:23.455Z</atom:updated>
            <content:encoded><![CDATA[<figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*Lh8CkaAhFoRvKPKxO-c26w.png" /></figure><p>In this article, I will review Scaling Egocentric Vision: The <a href="https://epic-kitchens.github.io/2022">EPIC-KITCHENS</a> Dataset.</p><p>Damen et al. [1] collect cooking videos with a <strong>first-person vision from 32 participants (10 nationalities). </strong>The dataset contains 55 hours of video, Our dataset features 55 hours, 39.6K action segments and 454.3K object bounding boxes.<strong> </strong>This egocentric view enables multi-tasking which makes the dataset more challenging. Each video contains object bounding boxes and action boundaries. Head-mounted GoPro is used to collect data.</p><p>They mentioned that all other egocentric datasets are scripted which means that all participants are told to read a script. However real life is more challenging, a chef may do multiple things at once (cooking and washing a few dishes) or change his mind during an action.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*XqrZX_JHZxrxb__gyFfgYg.png" /><figcaption>Dataset Statistics</figcaption></figure><p>As can be seen in the above figure, there are not only cooking annotations, the dataset also contains scenes of food preparation, washing, getting items, etc... The figure also shows sequence durations. Authors asked participants to annotate (explain actions) their own videos by themselves as a first coarse annotation since the best annotator for cooking videos can be chefs themselves.</p><p>Videos also have transcriptions. Authors collect these transcriptions via Amazon Mechanical Turk (AMT). Spoken language is not only English: 17 in English, 7 in Italian, 6 in Spanish, 1 in Greek, and 1 in Chinese. Videos in foreign languages are also transcripted to English via AMT. There is not any vocabulary limitation during narration.</p><h3>Action Annotations</h3><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*r3WHCEU8dkSNWSC6dnEvDw.png" /></figure><p>Annotators were also responsible for label narrated nouns.</p><h3>Verbs and Nouns</h3><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*Mk-FUf-aM-4ToEOLT4eB7Q.png" /></figure><p>They use SpaCy’s English core web model to extract verbs and nouns (Part-of-Speech). They grouped verbs into 125 classes and nouns into 331 classes.</p><p>[1] Damen, Dima, et al. “Scaling egocentric vision: The epic-kitchens dataset.” <em>Proceedings of the European Conference on Computer Vision (ECCV)</em>. 2018.</p><p><a href="https://epic-kitchens.github.io/2022">https://epic-kitchens.github.io/2022</a></p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=5e71ed117413" width="1" height="1" alt=""><hr><p><a href="https://medium.com/video-text-understanding/paper-review-scaling-egocentric-vision-the-epic-kitchens-dataset-5e71ed117413">Paper Review: Scaling Egocentric Vision: The EPIC-KITCHENS Dataset</a> was originally published in <a href="https://medium.com/video-text-understanding">Multi-Modal Understanding</a> on Medium, where people are continuing the conversation by highlighting and responding to this story.</p>]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[Paper Review: Towards Automatic Learning of Procedures from Web Instructional Videos]]></title>
            <link>https://medium.com/video-text-understanding/paper-review-towards-automatic-learning-of-procedures-from-web-instructional-videos-72f06aaae94e?source=rss----e5314efe8d52---4</link>
            <guid isPermaLink="false">https://medium.com/p/72f06aaae94e</guid>
            <category><![CDATA[video-processing]]></category>
            <category><![CDATA[dataset]]></category>
            <category><![CDATA[deep-learning]]></category>
            <category><![CDATA[food]]></category>
            <category><![CDATA[recipe]]></category>
            <dc:creator><![CDATA[Yunusemre Özköse]]></dc:creator>
            <pubDate>Sat, 02 Jul 2022 22:30:14 GMT</pubDate>
            <atom:updated>2022-07-02T22:30:14.083Z</atom:updated>
            <content:encoded><![CDATA[<figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*m5LjimuZZul13A1pX15lVQ.png" /></figure><p>In this article, I will review <em>Towards Automatic Learning of Procedures from Web Instructional Videos</em>.</p><p>Zhou et al. [1] introduce a recipe dataset that contains videos of cooking some foods and corresponding recipe information. It is called <a href="http://youcook2.eecs.umich.edu/">YouCook2</a>. Since video data is more informative than image data, I think it is more complicated to handle this type of data. It should be utilized as much as possible.</p><p>Procedural videos contain a lot of steps that build things. For example, a recipe video contains many steps to make dinner. Authors call these steps as <strong>segment. </strong>A segment may contain more than one action, but it should be explainable with one sentence.</p><p>Mainly they focus on procedure segmentation, introduce a new dataset: <strong>YouCook2</strong> and propose <strong>ProcNets </strong>to<strong> </strong>propose video segments from a given video. The dataset contains 2000 videos from 89 recipes, totally 176 hours. The proposed model is free of number of segment knowledge or available subtitles.</p><p>Procedural segmentation is very similar to event proposing, but event proposing aims to extract uncategorized temporal segments from the given video. Hence recall is more important in this task. However, procedure segmenting aims to identify segments that are actually a set member.</p><h3>Automatic procedure segmentation method</h3><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*6TaKqqdR9bSzogSimoN8XA.png" /></figure><p>There are 3 main components of the proposed model:</p><ol><li><strong>Context-Aware Video Embedding:</strong> Video frames are fed to ResNet model and ResNet extracts Lx512 dimensional feature matrix where L is number of frames. L is set to 500. Then a bi-directional LSTM is used to obtain context encodings. After that, Resnet features, forward and backward outputs of LSTM are concatenated. Finally, dimension is reduced to Lx512 with a linear layer. Final Lx512 matrix is called frame-wise context-aware features.</li><li><strong>Procedure Segment Proposal:</strong> They barrow anchoring idea from faster R-CNN. There are k number of anchor that is applied to context-aware features. So, if we have Lx512 features and apply anchoring, we obtain kxLx3 matrix which stands for segment proposal. Each proposal has proposal score, center and length offsets. Sigmoid and tanh are applied to proposal score and offsets respectively. During training, binary cross-entropy is used with proposal scores and L1 loss is applied to offsets.</li><li><strong>Sequential Prediction:</strong> Obtained procedure scores and offsets are converted to proposal vector (flattened) and this vector is fed to another LSTM with Resnet features. After that, beam search is applied to find the best sequence for proposed segment. Empirically, reported best beam size is 1, it is actually greedily selecting the best one :).</li></ol><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*B8KsWLHzkY6LKLwNwQ434g.png" /></figure><h3>Loss</h3><p>There are 3 parts of the loss function. The first one is from proposal network. They select positive samples with &gt;0.8 UoI scores and negative samples with &lt;0.2 UoI scores. The second one is again from proposal network. They use L1 loss for offsets of proposals. The third one is negative log-likelihood for LSTM outputs.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*CaE4771vwPNRn3jGUTSIRA.png" /></figure><h3>References</h3><p>[1] Zhou, Luowei, Chenliang Xu, and Jason J. Corso. “Towards automatic learning of procedures from web instructional videos.” <em>Thirty-Second AAAI Conference on Artificial Intelligence</em>. 2018.<br>[2] <a href="http://youcook2.eecs.umich.edu/">http://youcook2.eecs.umich.edu</a></p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=72f06aaae94e" width="1" height="1" alt=""><hr><p><a href="https://medium.com/video-text-understanding/paper-review-towards-automatic-learning-of-procedures-from-web-instructional-videos-72f06aaae94e">Paper Review: Towards Automatic Learning of Procedures from Web Instructional Videos</a> was originally published in <a href="https://medium.com/video-text-understanding">Multi-Modal Understanding</a> on Medium, where people are continuing the conversation by highlighting and responding to this story.</p>]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[Hierarchy of Publications]]></title>
            <link>https://medium.com/video-text-understanding/hierarchy-b9e49b70e7c8?source=rss----e5314efe8d52---4</link>
            <guid isPermaLink="false">https://medium.com/p/b9e49b70e7c8</guid>
            <dc:creator><![CDATA[Yunusemre Özköse]]></dc:creator>
            <pubDate>Sun, 05 Jun 2022 14:09:36 GMT</pubDate>
            <atom:updated>2022-07-04T21:51:29.592Z</atom:updated>
            <content:encoded><![CDATA[<h3>Datasets</h3><ul><li><strong>TIPS:</strong> <a href="https://medium.com/video-text-understanding/paper-review-learning-temporal-video-procedure-segmentation-from-an-automatically-collected-large-1cfb618b9339">2020, Learning Temporal Video Procedure Segmentation from an Automatically Collected Large Dataset</a></li><li><strong>YouCook2:</strong> <a href="https://medium.com/video-text-understanding/paper-review-towards-automatic-learning-of-procedures-from-web-instructional-videos-72f06aaae94e">2018, Towards Automatic Learning of Procedures from Web Instructional Videos</a></li><li><strong>Epic Kitchen:</strong> <a href="https://medium.com/video-text-understanding/paper-review-scaling-egocentric-vision-the-epic-kitchens-dataset-5e71ed117413">2018, Scaling Egocentric Vision: The EPIC-KITCHENS Dataset</a></li><li><strong>Recipe1M:</strong> <a href="https://medium.com/video-text-understanding/paper-review-learning-cross-modal-embeddings-for-cooking-recipes-and-food-images-14e06b9141e">2017, Learning Cross-modal Embeddings for Cooking Recipes and Food Images</a></li></ul><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=b9e49b70e7c8" width="1" height="1" alt=""><hr><p><a href="https://medium.com/video-text-understanding/hierarchy-b9e49b70e7c8">Hierarchy of Publications</a> was originally published in <a href="https://medium.com/video-text-understanding">Multi-Modal Understanding</a> on Medium, where people are continuing the conversation by highlighting and responding to this story.</p>]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[Paper Review: Learning Cross-modal Embeddings for Cooking Recipes and Food Images]]></title>
            <link>https://medium.com/video-text-understanding/paper-review-learning-cross-modal-embeddings-for-cooking-recipes-and-food-images-14e06b9141e?source=rss----e5314efe8d52---4</link>
            <guid isPermaLink="false">https://medium.com/p/14e06b9141e</guid>
            <category><![CDATA[deep-learning]]></category>
            <category><![CDATA[video-text-understanding]]></category>
            <dc:creator><![CDATA[Yunusemre Özköse]]></dc:creator>
            <pubDate>Sun, 05 Jun 2022 14:08:30 GMT</pubDate>
            <atom:updated>2022-07-17T12:37:57.079Z</atom:updated>
            <content:encoded><![CDATA[<figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*kyi3__18ks35ExZO8THjkw.png" /><figcaption>Figure 1 in [1]</figcaption></figure><p>In this article, I will review <em>Learning Cross-modal Embeddings for Cooking Recipes and Food Images</em>.</p><p>Salvador et al. [1] propose a feature extraction method that composes textual and visual information for recipes. They also introduce a new dataset, <a href="http://pic2recipe.csail.mit.edu/"><em>Recipe1M</em></a><em>. </em>The dataset consists of recipes that actually contain 3 components: <strong>images, ingredients, and instructions</strong>. High-level pipeline is</p><p>1. Encode ingredients with LSTM<br>2. Encode instructions with another LSTM<br>3. Concatenate them and obtain 1 textual embedding<br>4. Extract visual features of the image with Resnet50 or VGG16<br>5. Feed visual and textual embeddings to different fully connected layers.<br>6. Calculate losses.</p><h3>Dataset</h3><p>The authors introduce a new dataset which is called Recipe1M. The key components of the recipes are</p><ul><li>Images: food images of corresponding recipes. Images usually show the final state of the recipe, taken from the top and closely. Foods may be in a saucepan (I see this state mostly.) or in a dish. Some images may not be clear because they are taken so close.</li></ul><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*QjfP_vecauD1CZCh3Cbs2A.jpeg" /></figure><figure><img alt="" src="https://cdn-images-1.medium.com/max/256/1*KoZoxPPcI67rgl3IjLruMw.jpeg" /></figure><figure><img alt="" src="https://cdn-images-1.medium.com/max/512/1*53g7P2Fevx_PKlIrmi8b9A.jpeg" /><figcaption>Images from Recipe1M dataset</figcaption></figure><ul><li>Ingredients: An example for Mac and Cheese is given below (both ingredients and instructions).</li></ul><blockquote>6 ounces penne<br>2 cups Beechers Flagship Cheese Sauce (recipe follows)<br>1 ounce Cheddar, grated (1/4 cup)<br>1 ounce Gruyere cheese, grated (1/4 cup)<br>…</blockquote><ul><li>Instructions:</li></ul><blockquote>1. Preheat the oven to 350 F. Butter or oil an 8-inch baking dish.<br>2. Cook the penne 2 minutes less than package directions.<br>3. (It will finish cooking in the oven.)<br>4. Rinse the pasta in cold water and set aside.<br>…</blockquote><p>In images, we may not see all ingredients. We can’t track instructions. Hence we have to carefully design a learning pipeline that model can learn what can a person do with these ingredients and steps.</p><h4>Dataset Statistics</h4><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*B5twwVjESReIKo6RAnUwhw.png" /></figure><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*DXqzljPwzGI_5qV0R09M8Q.png" /><figcaption>Figure 2 and Table 1 in [1]</figcaption></figure><h3>Approach</h3><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*vdv6vSnKQ1SF8GrpXDDK_g.png" /><figcaption>Figure 3 in [1]</figcaption></figure><p>An overview of the proposed approach is given above. We can divide the pipeline into steps as follows</p><ol><li>Ingredient keywords are extracted before training. For example, <em>2 tbsp of olive oil </em>is converted to<em> olive_oil.</em> A bidirectional LSTM is trained to extract ingredient names. They don’t discuss too much about this model but mentioned that the accuracy of the ingredient name extraction model is %99.5. They label a small portion of the data for this task.</li><li>After extracting ingredient names, they obtain word2vec representations of them.</li><li>Authors believe that a single LSTM can’t learn from the whole recipe sequence because of the long lengths. Hence they use a two-stage LSTM. First, sentences are encoded with the first LSTM. Outputs of the first LSTM are called <em>skip-instructions.</em> Then skip instructions are fed to the second LSTM.</li><li>The output of 2 LSTMs (LSTMs of skip-instructions and ingredient names) is concatenated. In this way, we obtain a textual embedding.</li><li>In parallel, the recipe image is given to a backbone which can be Resnet50 or VGG16. They remove the softmax layer of the networks and take the last layer outputs as visual embedding.</li><li>At this point, joint learning starts. Both semantic and visual embeddings are fed to 2 different fully connected layers for projecting into <strong>recipe-image joint space. </strong>In this step, embeddings are wanted to make as much as closer to each other.</li></ol><h3>Training</h3><p>After joint learning, cosine similarity loss is calculated as follows.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*JOW7wZns-1kOpG2cyh-etw.png" /><figcaption>Cosine similarity loss</figcaption></figure><p>During training, positive and negative recipe-image pairs are used. In addition to loss, authors add a semantic regularization to the loss for better alignment between image-recipe pairs. They believe that if different modalities share weights during training, learning representations become easier.</p><h3>Implementation</h3><p>Code is publicly available <a href="https://github.com/torralba-lab/im2recipe-Pytorch">here</a>.</p><h3>References</h3><p>[1] Salvador, Amaia, et al. “Learning cross-modal embeddings for cooking recipes and food images.” <em>Proceedings of the IEEE conference on computer vision and pattern recognition</em>. 2017.</p><p>[2] <a href="https://github.com/torralba-lab/im2recipe-Pytorch">https://github.com/torralba-lab/im2recipe-Pytorch</a></p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=14e06b9141e" width="1" height="1" alt=""><hr><p><a href="https://medium.com/video-text-understanding/paper-review-learning-cross-modal-embeddings-for-cooking-recipes-and-food-images-14e06b9141e">Paper Review: Learning Cross-modal Embeddings for Cooking Recipes and Food Images</a> was originally published in <a href="https://medium.com/video-text-understanding">Multi-Modal Understanding</a> on Medium, where people are continuing the conversation by highlighting and responding to this story.</p>]]></content:encoded>
        </item>
    </channel>
</rss>